Instructions to use ApacheOne/SD15_MACaQ_pruned_fullwidth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ApacheOne/SD15_MACaQ_pruned_fullwidth with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ApacheOne/SD15_MACaQ_pruned_fullwidth", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
SD15 MACaQ Pruned Full-Width
72.84% smaller U-Net weight payload ยท 1,719.04 MB FP16 โ 466.96 MB (445.32 MiB) packed.
This is an MXFP4 W4A4 quantization of Stable Yogi SD 1.5 V9 LCM. It retains the original U-Net layer dimensions. The repository name follows the earlier MACaQ release. The storage savings come from weight quantization, and all U-Net layers remain present.
Weights
| Component | Precision | Tensor payload |
|---|---|---|
| U-Net | MXFP4 W4A4 with retained higher-precision tensors | 466.96 MB |
| CLIP text encoder | FP16 | 246.12 MB |
| VAE | FP16 | 167.31 MB |
| Total weight files including headers | 880.62 MB |
Full-width calibration
The U-Net was refit from the original FP16 checkpoint. Calibration sampled activations from 32 prompts with up to 128 rows per forward call. Each of the 184 linear layers and 98 convolutions used a Hessian that spans its full input width, including flattened convolution patch channels, with alignment padding to multiples of 32 where needed. The widest layer used 23,040 inputs. The earlier release used 256-wide convolution Hessian blocks.
The fit balances input channels, applies a blockwise Hadamard rotation, screens block exponents, then refines adjacent FP4 weight codes using the full Hessian at fixed exponents. Each row is refined to a local stopping criterion. Per-layer sample counts, widths, flip counts, and objectives are in the run report.
FP16 comparisons
Six matched prompt-and-seed pairs were rendered at 512ร512 using LCM, 4 steps, and CFG 1.2. The left image is FP16 and the right image uses the quantized U-Net. Both use the same CLIP text encoder and VAE. The quantized column used emulated MXFP4 W4A4 on the L4, with FP4 rounding and BF16 matrix multiplication.
The mean LPIPS to FP16 was 0.4292 across these six pairs. Lower values indicate closer image appearance. Some details change, including glasses in the train-station scene and the car's viewing angle. The earlier release's results were reported with SSIM, so this LPIPS result does not rank the two releases.
Seed 7001 ยท Candid photo of an adult man holding a newspaper at a train station ยท LPIPS 0.3830
Seed 7002 ยท A full-body photograph of an adult woman in a long blue coat at dusk ยท LPIPS 0.3491
Seed 7003 ยท Close-up of a ceramic teapot, two cups, and a linen napkin on a table ยท LPIPS 0.3947
Seed 7004 ยท A red vintage car parked on a curve in a desert highway, sunny afternoon ยท LPIPS 0.4756
Seed 7005 ยท Portrait of an adult architect wearing black rectangular glasses in a sunlit studio ยท LPIPS 0.4408
Seed 7006 ยท Exactly three green apples beside one yellow pear on a wooden board ยท LPIPS 0.5322
U-Net layer inventory
The JSON inventory includes every stored U-Net tensor.
| Layer group | Modules | Storage (MiB) |
|---|---|---|
| 3ร3 convolutions | 52 | 276.21 |
| Normalization | 109 | 0.38 |
| 1ร1 convolutions | 46 | 25.66 |
| Attention projections | 128 | 50.06 |
| MLP projections | 32 | 78.63 |
| Timestep and other linears | 24 | 14.38 |
3ร3 convolutions ยท 52 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
conv_in |
MXFP4 W4A4 | 320ร4ร3ร3 | 64 | 46,720 | B_inv_T BF16 [32ร32], W_packed U8 [320ร128], W_scales U8 [320ร8], bias BF16 [320], pre_scale BF16 [256] |
conv_out |
MXFP4 W4A4 | 4ร320ร3ร3 | 2,880 | 14,728 | B_inv_T BF16 [32ร32], W_packed U8 [4ร1536], W_scales U8 [4ร96], bias BF16 [4], pre_scale BF16 [3072] |
down_blocks.0.downsamplers.0.conv |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
down_blocks.0.resnets.0.conv1 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
down_blocks.0.resnets.0.conv2 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
down_blocks.0.resnets.1.conv1 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
down_blocks.0.resnets.1.conv2 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
down_blocks.1.downsamplers.0.conv |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
down_blocks.1.resnets.0.conv1 |
MXFP4 W4A4 | 640ร320ร3ร3 | 2,880 | 1,053,952 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1536], W_scales U8 [640ร96], bias BF16 [640], pre_scale BF16 [3072] |
down_blocks.1.resnets.0.conv2 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
down_blocks.1.resnets.1.conv1 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
down_blocks.1.resnets.1.conv2 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
down_blocks.2.downsamplers.0.conv |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.2.resnets.0.conv1 |
MXFP4 W4A4 | 1280ร640ร3ร3 | 5,760 | 4,020,224 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2944], W_scales U8 [1280ร184], bias BF16 [1280], pre_scale BF16 [5888] |
down_blocks.2.resnets.0.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.2.resnets.1.conv1 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.2.resnets.1.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.3.resnets.0.conv1 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.3.resnets.0.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.3.resnets.1.conv1 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
down_blocks.3.resnets.1.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
mid_block.resnets.0.conv1 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
mid_block.resnets.0.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
mid_block.resnets.1.conv1 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
mid_block.resnets.1.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.0.resnets.0.conv1 |
MXFP4 W4A4 | 1280ร2560ร3ร3 | 23,040 | 15,717,888 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร11520], W_scales U8 [1280ร720], bias BF16 [1280], pre_scale BF16 [23040] |
up_blocks.0.resnets.0.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.0.resnets.1.conv1 |
MXFP4 W4A4 | 1280ร2560ร3ร3 | 23,040 | 15,717,888 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร11520], W_scales U8 [1280ร720], bias BF16 [1280], pre_scale BF16 [23040] |
up_blocks.0.resnets.1.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.0.resnets.2.conv1 |
MXFP4 W4A4 | 1280ร2560ร3ร3 | 23,040 | 15,717,888 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร11520], W_scales U8 [1280ร720], bias BF16 [1280], pre_scale BF16 [23040] |
up_blocks.0.resnets.2.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.0.upsamplers.0.conv |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.1.resnets.0.conv1 |
MXFP4 W4A4 | 1280ร2560ร3ร3 | 23,040 | 15,717,888 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร11520], W_scales U8 [1280ร720], bias BF16 [1280], pre_scale BF16 [23040] |
up_blocks.1.resnets.0.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.1.resnets.1.conv1 |
MXFP4 W4A4 | 1280ร2560ร3ร3 | 23,040 | 15,717,888 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร11520], W_scales U8 [1280ร720], bias BF16 [1280], pre_scale BF16 [23040] |
up_blocks.1.resnets.1.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.1.resnets.2.conv1 |
MXFP4 W4A4 | 1280ร1920ร3ร3 | 17,280 | 11,876,864 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร8704], W_scales U8 [1280ร544], bias BF16 [1280], pre_scale BF16 [17408] |
up_blocks.1.resnets.2.conv2 |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.1.upsamplers.0.conv |
MXFP4 W4A4 | 1280ร1280ร3ร3 | 11,520 | 7,861,248 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร5760], W_scales U8 [1280ร360], bias BF16 [1280], pre_scale BF16 [11520] |
up_blocks.2.resnets.0.conv1 |
MXFP4 W4A4 | 640ร1920ร3ร3 | 17,280 | 5,956,864 | B_inv_T BF16 [32ร32], W_packed U8 [640ร8704], W_scales U8 [640ร544], bias BF16 [640], pre_scale BF16 [17408] |
up_blocks.2.resnets.0.conv2 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
up_blocks.2.resnets.1.conv1 |
MXFP4 W4A4 | 640ร1280ร3ร3 | 11,520 | 3,943,168 | B_inv_T BF16 [32ร32], W_packed U8 [640ร5760], W_scales U8 [640ร360], bias BF16 [640], pre_scale BF16 [11520] |
up_blocks.2.resnets.1.conv2 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
up_blocks.2.resnets.2.conv1 |
MXFP4 W4A4 | 640ร960ร3ร3 | 8,640 | 2,980,096 | B_inv_T BF16 [32ร32], W_packed U8 [640ร4352], W_scales U8 [640ร272], bias BF16 [640], pre_scale BF16 [8704] |
up_blocks.2.resnets.2.conv2 |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
up_blocks.2.upsamplers.0.conv |
MXFP4 W4A4 | 640ร640ร3ร3 | 5,760 | 2,017,024 | B_inv_T BF16 [32ร32], W_packed U8 [640ร2944], W_scales U8 [640ร184], bias BF16 [640], pre_scale BF16 [5888] |
up_blocks.3.resnets.0.conv1 |
MXFP4 W4A4 | 320ร960ร3ร3 | 8,640 | 1,499,776 | B_inv_T BF16 [32ร32], W_packed U8 [320ร4352], W_scales U8 [320ร272], bias BF16 [320], pre_scale BF16 [8704] |
up_blocks.3.resnets.0.conv2 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
up_blocks.3.resnets.1.conv1 |
MXFP4 W4A4 | 320ร640ร3ร3 | 5,760 | 1,015,424 | B_inv_T BF16 [32ร32], W_packed U8 [320ร2944], W_scales U8 [320ร184], bias BF16 [320], pre_scale BF16 [5888] |
up_blocks.3.resnets.1.conv2 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
up_blocks.3.resnets.2.conv1 |
MXFP4 W4A4 | 320ร640ร3ร3 | 5,760 | 1,015,424 | B_inv_T BF16 [32ร32], W_packed U8 [320ร2944], W_scales U8 [320ร184], bias BF16 [320], pre_scale BF16 [5888] |
up_blocks.3.resnets.2.conv2 |
MXFP4 W4A4 | 320ร320ร3ร3 | 2,880 | 531,072 | B_inv_T BF16 [32ร32], W_packed U8 [320ร1536], W_scales U8 [320ร96], bias BF16 [320], pre_scale BF16 [3072] |
Normalization ยท 109 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
conv_norm_out |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.0.norm |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.0.transformer_blocks.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.0.transformer_blocks.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.0.transformer_blocks.0.norm3 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.1.norm |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.1.transformer_blocks.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.1.transformer_blocks.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.attentions.1.transformer_blocks.0.norm3 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.resnets.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.resnets.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.resnets.1.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.0.resnets.1.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.1.attentions.0.norm |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.0.transformer_blocks.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.0.transformer_blocks.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.0.transformer_blocks.0.norm3 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.1.norm |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.1.transformer_blocks.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.1.transformer_blocks.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.attentions.1.transformer_blocks.0.norm3 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.resnets.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
down_blocks.1.resnets.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.resnets.1.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.1.resnets.1.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.2.attentions.0.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.1.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.resnets.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
down_blocks.2.resnets.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.resnets.1.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.2.resnets.1.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.3.resnets.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.3.resnets.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.3.resnets.1.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
down_blocks.3.resnets.1.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.attentions.0.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.attentions.0.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.attentions.0.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.attentions.0.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.resnets.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.resnets.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.resnets.1.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
mid_block.resnets.1.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.0.resnets.0.norm1 |
F16 | 2560 | โ | 10,240 | bias F16 [2560], weight F16 [2560] |
up_blocks.0.resnets.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.0.resnets.1.norm1 |
F16 | 2560 | โ | 10,240 | bias F16 [2560], weight F16 [2560] |
up_blocks.0.resnets.1.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.0.resnets.2.norm1 |
F16 | 2560 | โ | 10,240 | bias F16 [2560], weight F16 [2560] |
up_blocks.0.resnets.2.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.0.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.1.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.2.norm |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.norm3 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.resnets.0.norm1 |
F16 | 2560 | โ | 10,240 | bias F16 [2560], weight F16 [2560] |
up_blocks.1.resnets.0.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.resnets.1.norm1 |
F16 | 2560 | โ | 10,240 | bias F16 [2560], weight F16 [2560] |
up_blocks.1.resnets.1.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.1.resnets.2.norm1 |
F16 | 1920 | โ | 7,680 | bias F16 [1920], weight F16 [1920] |
up_blocks.1.resnets.2.norm2 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.2.attentions.0.norm |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.0.transformer_blocks.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.0.transformer_blocks.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.0.transformer_blocks.0.norm3 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.1.norm |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.1.transformer_blocks.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.1.transformer_blocks.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.1.transformer_blocks.0.norm3 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.2.norm |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.2.transformer_blocks.0.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.2.transformer_blocks.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.attentions.2.transformer_blocks.0.norm3 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.resnets.0.norm1 |
F16 | 1920 | โ | 7,680 | bias F16 [1920], weight F16 [1920] |
up_blocks.2.resnets.0.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.resnets.1.norm1 |
F16 | 1280 | โ | 5,120 | bias F16 [1280], weight F16 [1280] |
up_blocks.2.resnets.1.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.2.resnets.2.norm1 |
F16 | 960 | โ | 3,840 | bias F16 [960], weight F16 [960] |
up_blocks.2.resnets.2.norm2 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.3.attentions.0.norm |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.0.transformer_blocks.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.0.transformer_blocks.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.0.transformer_blocks.0.norm3 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.1.norm |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.1.transformer_blocks.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.1.transformer_blocks.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.1.transformer_blocks.0.norm3 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.2.norm |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.2.transformer_blocks.0.norm1 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.2.transformer_blocks.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.attentions.2.transformer_blocks.0.norm3 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.resnets.0.norm1 |
F16 | 960 | โ | 3,840 | bias F16 [960], weight F16 [960] |
up_blocks.3.resnets.0.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.resnets.1.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.3.resnets.1.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
up_blocks.3.resnets.2.norm1 |
F16 | 640 | โ | 2,560 | bias F16 [640], weight F16 [640] |
up_blocks.3.resnets.2.norm2 |
F16 | 320 | โ | 1,280 | bias F16 [320], weight F16 [320] |
1ร1 convolutions ยท 46 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
down_blocks.0.attentions.0.proj_in |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.0.proj_out |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.1.proj_in |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.1.proj_out |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.1.attentions.0.proj_in |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.0.proj_out |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.1.proj_in |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.1.proj_out |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.resnets.0.conv_shortcut |
MXFP4 W4A4 | 640ร320ร1ร1 | 320 | 178,432 | B_inv_T BF16 [32ร32], W_packed U8 [640ร256], W_scales U8 [640ร16], bias BF16 [640], pre_scale BF16 [512] |
down_blocks.2.attentions.0.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.resnets.0.conv_shortcut |
MXFP4 W4A4 | 1280ร640ร1ร1 | 640 | 528,384 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], bias BF16 [1280], pre_scale BF16 [768] |
mid_block.attentions.0.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
mid_block.attentions.0.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.0.resnets.0.conv_shortcut |
MXFP4 W4A4 | 1280ร2560ร1ร1 | 2,560 | 1,750,528 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1280], W_scales U8 [1280ร80], bias BF16 [1280], pre_scale BF16 [2560] |
up_blocks.0.resnets.1.conv_shortcut |
MXFP4 W4A4 | 1280ร2560ร1ร1 | 2,560 | 1,750,528 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1280], W_scales U8 [1280ร80], bias BF16 [1280], pre_scale BF16 [2560] |
up_blocks.0.resnets.2.conv_shortcut |
MXFP4 W4A4 | 1280ร2560ร1ร1 | 2,560 | 1,750,528 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1280], W_scales U8 [1280ร80], bias BF16 [1280], pre_scale BF16 [2560] |
up_blocks.1.attentions.0.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.proj_in |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.proj_out |
MXFP4 W4A4 | 1280ร1280ร1ร1 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.resnets.0.conv_shortcut |
MXFP4 W4A4 | 1280ร2560ร1ร1 | 2,560 | 1,750,528 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1280], W_scales U8 [1280ร80], bias BF16 [1280], pre_scale BF16 [2560] |
up_blocks.1.resnets.1.conv_shortcut |
MXFP4 W4A4 | 1280ร2560ร1ร1 | 2,560 | 1,750,528 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1280], W_scales U8 [1280ร80], bias BF16 [1280], pre_scale BF16 [2560] |
up_blocks.1.resnets.2.conv_shortcut |
MXFP4 W4A4 | 1280ร1920ร1ร1 | 1,920 | 1,401,344 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร1024], W_scales U8 [1280ร64], bias BF16 [1280], pre_scale BF16 [2048] |
up_blocks.2.attentions.0.proj_in |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.0.proj_out |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.1.proj_in |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.1.proj_out |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.2.proj_in |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.2.proj_out |
MXFP4 W4A4 | 640ร640ร1ร1 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.resnets.0.conv_shortcut |
MXFP4 W4A4 | 640ร1920ร1ร1 | 1,920 | 703,744 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1024], W_scales U8 [640ร64], bias BF16 [640], pre_scale BF16 [2048] |
up_blocks.2.resnets.1.conv_shortcut |
MXFP4 W4A4 | 640ร1280ร1ร1 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
up_blocks.2.resnets.2.conv_shortcut |
MXFP4 W4A4 | 640ร960ร1ร1 | 960 | 353,536 | B_inv_T BF16 [32ร32], W_packed U8 [640ร512], W_scales U8 [640ร32], bias BF16 [640], pre_scale BF16 [1024] |
up_blocks.3.attentions.0.proj_in |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.0.proj_out |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.1.proj_in |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.1.proj_out |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.2.proj_in |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.2.proj_out |
MXFP4 W4A4 | 320ร320ร1ร1 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.resnets.0.conv_shortcut |
MXFP4 W4A4 | 320ร960ร1ร1 | 960 | 178,816 | B_inv_T BF16 [32ร32], W_packed U8 [320ร512], W_scales U8 [320ร32], bias BF16 [320], pre_scale BF16 [1024] |
up_blocks.3.resnets.1.conv_shortcut |
MXFP4 W4A4 | 320ร640ร1ร1 | 640 | 134,784 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], bias BF16 [320], pre_scale BF16 [768] |
up_blocks.3.resnets.2.conv_shortcut |
MXFP4 W4A4 | 320ร640ร1ร1 | 640 | 134,784 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], bias BF16 [320], pre_scale BF16 [768] |
Attention projections ยท 128 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
mid_block.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
mid_block.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 875,008 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 1280ร768 | 768 | 525,824 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร384], W_scales U8 [1280ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 640ร640 | 640 | 265,984 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], bias BF16 [640], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 640ร640 | 640 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 640ร768 | 768 | 264,704 | B_inv_T BF16 [32ร32], W_packed U8 [640ร384], W_scales U8 [640ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_k |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_v |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_out.0 |
MXFP4 W4A4 | 320ร320 | 320 | 90,752 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], bias BF16 [320], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_q |
MXFP4 W4A4 | 320ร320 | 320 | 90,112 | B_inv_T BF16 [32ร32], W_packed U8 [320ร256], W_scales U8 [320ร16], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v |
MXFP4 W4A4 | 320ร768 | 768 | 134,144 | B_inv_T BF16 [32ร32], W_packed U8 [320ร384], W_scales U8 [320ร24], pre_scale BF16 [768] |
MLP projections ยท 32 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
down_blocks.0.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 2560ร320 | 320 | 704,512 | B_inv_T BF16 [32ร32], W_packed U8 [2560ร256], W_scales U8 [2560ร16], bias BF16 [2560], pre_scale BF16 [512] |
down_blocks.0.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
down_blocks.0.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 2560ร320 | 320 | 704,512 | B_inv_T BF16 [32ร32], W_packed U8 [2560ร256], W_scales U8 [2560ร16], bias BF16 [2560], pre_scale BF16 [512] |
down_blocks.0.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
down_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 5120ร640 | 640 | 2,102,784 | B_inv_T BF16 [32ร32], W_packed U8 [5120ร384], W_scales U8 [5120ร24], bias BF16 [5120], pre_scale BF16 [768] |
down_blocks.1.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 640ร2560 | 2,560 | 878,848 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1280], W_scales U8 [640ร80], bias BF16 [640], pre_scale BF16 [2560] |
down_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 5120ร640 | 640 | 2,102,784 | B_inv_T BF16 [32ร32], W_packed U8 [5120ร384], W_scales U8 [5120ร24], bias BF16 [5120], pre_scale BF16 [768] |
down_blocks.1.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 640ร2560 | 2,560 | 878,848 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1280], W_scales U8 [640ร80], bias BF16 [640], pre_scale BF16 [2560] |
down_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
down_blocks.2.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
down_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
down_blocks.2.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
mid_block.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
mid_block.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
up_blocks.1.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
up_blocks.1.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
up_blocks.1.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
up_blocks.1.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
up_blocks.1.attentions.2.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 10240ร1280 | 1,280 | 6,988,288 | B_inv_T BF16 [32ร32], W_packed U8 [10240ร640], W_scales U8 [10240ร40], bias BF16 [10240], pre_scale BF16 [1280] |
up_blocks.1.attentions.2.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 1280ร5120 | 5,120 | 3,496,448 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร2560], W_scales U8 [1280ร160], bias BF16 [1280], pre_scale BF16 [5120] |
up_blocks.2.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 5120ร640 | 640 | 2,102,784 | B_inv_T BF16 [32ร32], W_packed U8 [5120ร384], W_scales U8 [5120ร24], bias BF16 [5120], pre_scale BF16 [768] |
up_blocks.2.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 640ร2560 | 2,560 | 878,848 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1280], W_scales U8 [640ร80], bias BF16 [640], pre_scale BF16 [2560] |
up_blocks.2.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 5120ร640 | 640 | 2,102,784 | B_inv_T BF16 [32ร32], W_packed U8 [5120ร384], W_scales U8 [5120ร24], bias BF16 [5120], pre_scale BF16 [768] |
up_blocks.2.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 640ร2560 | 2,560 | 878,848 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1280], W_scales U8 [640ร80], bias BF16 [640], pre_scale BF16 [2560] |
up_blocks.2.attentions.2.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 5120ร640 | 640 | 2,102,784 | B_inv_T BF16 [32ร32], W_packed U8 [5120ร384], W_scales U8 [5120ร24], bias BF16 [5120], pre_scale BF16 [768] |
up_blocks.2.attentions.2.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 640ร2560 | 2,560 | 878,848 | B_inv_T BF16 [32ร32], W_packed U8 [640ร1280], W_scales U8 [640ร80], bias BF16 [640], pre_scale BF16 [2560] |
up_blocks.3.attentions.0.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 2560ร320 | 320 | 704,512 | B_inv_T BF16 [32ร32], W_packed U8 [2560ร256], W_scales U8 [2560ร16], bias BF16 [2560], pre_scale BF16 [512] |
up_blocks.3.attentions.0.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
up_blocks.3.attentions.1.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 2560ร320 | 320 | 704,512 | B_inv_T BF16 [32ร32], W_packed U8 [2560ร256], W_scales U8 [2560ร16], bias BF16 [2560], pre_scale BF16 [512] |
up_blocks.3.attentions.1.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
up_blocks.3.attentions.2.transformer_blocks.0.ff.net.0.proj |
MXFP4 W4A4 | 2560ร320 | 320 | 704,512 | B_inv_T BF16 [32ร32], W_packed U8 [2560ร256], W_scales U8 [2560ร16], bias BF16 [2560], pre_scale BF16 [512] |
up_blocks.3.attentions.2.transformer_blocks.0.ff.net.2 |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
Timestep and other linears ยท 24 layers
| Layer | Precision | Original weight shape | Hessian width | Stored bytes | Tensor dtypes and shapes |
|---|---|---|---|---|---|
down_blocks.0.resnets.0.time_emb_proj |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
down_blocks.0.resnets.1.time_emb_proj |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
down_blocks.1.resnets.0.time_emb_proj |
MXFP4 W4A4 | 640ร1280 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
down_blocks.1.resnets.1.time_emb_proj |
MXFP4 W4A4 | 640ร1280 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
down_blocks.2.resnets.0.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.2.resnets.1.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.3.resnets.0.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
down_blocks.3.resnets.1.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
mid_block.resnets.0.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
mid_block.resnets.1.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
time_embedding.linear_1 |
MXFP4 W4A4 | 1280ร320 | 320 | 353,792 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร256], W_scales U8 [1280ร16], bias BF16 [1280], pre_scale BF16 [512] |
time_embedding.linear_2 |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.0.resnets.0.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.0.resnets.1.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.0.resnets.2.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.resnets.0.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.resnets.1.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.1.resnets.2.time_emb_proj |
MXFP4 W4A4 | 1280ร1280 | 1,280 | 877,568 | B_inv_T BF16 [32ร32], W_packed U8 [1280ร640], W_scales U8 [1280ร40], bias BF16 [1280], pre_scale BF16 [1280] |
up_blocks.2.resnets.0.time_emb_proj |
MXFP4 W4A4 | 640ร1280 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
up_blocks.2.resnets.1.time_emb_proj |
MXFP4 W4A4 | 640ร1280 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
up_blocks.2.resnets.2.time_emb_proj |
MXFP4 W4A4 | 640ร1280 | 1,280 | 441,088 | B_inv_T BF16 [32ร32], W_packed U8 [640ร640], W_scales U8 [640ร40], bias BF16 [640], pre_scale BF16 [1280] |
up_blocks.3.resnets.0.time_emb_proj |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
up_blocks.3.resnets.1.time_emb_proj |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
up_blocks.3.resnets.2.time_emb_proj |
MXFP4 W4A4 | 320ร1280 | 1,280 | 222,848 | B_inv_T BF16 [32ร32], W_packed U8 [320ร640], W_scales U8 [320ร40], bias BF16 [320], pre_scale BF16 [1280] |
Run locally
Use CUDA PyTorch with Triton, Diffusers 0.39.0, Transformers 4.57.6, Accelerate, Safetensors, and Hugging Face Hub. The packed U-Net uses the included custom loader. Use backend="native" for native MXFP4 on a compatible Blackwell setup, or backend="emulated" to reproduce the L4 evaluation. Native inference was outside the reported test.
import sys
from pathlib import Path
import torch
from huggingface_hub import snapshot_download
directory = Path(snapshot_download("ApacheOne/SD15_MACaQ_pruned_fullwidth"))
sys.path.insert(0, str(directory))
from load_pipeline import load_pipeline
torch.backends.cuda.matmul.allow_bf16_reduced_precision_reduction = False
pipe = load_pipeline(directory, device="cuda", backend="emulated")
image = pipe(
"A ceramic teapot on a wooden table",
height=512, width=512,
num_inference_steps=4, guidance_scale=1.2,
generator=torch.Generator("cuda").manual_seed(7003),
).images[0]
image.save("macaq_fullwidth.png")
Sources and terms
- Stable Yogi SD 1.5 V9 LCM source checkpoint, version 1235013.
- Stable Yogi checkpoint collection and source terms.
- MACaQ method and reference runtime. Runtime license and notices are under
unet/runtime/macaq_vendor. - Earlier MACaQ release.
Source checkpoint SHA-256 is 1a16a9524427019dc513b398087035e7e36ad2f2aa9691bd71d28ad959e94180.
- Downloads last month
- -





