Atomic Chat

Team

company

Verified

https://atomic.chat

AI & ML interests

Local Models Server and Free Ai Chat app

Recent Activity

notforu777 updated a collection about 7 hours ago

DeepSeek-V4.1-Flash-1017 Uncensored

notforu777 published a model about 7 hours ago

AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-DwarfStar-GGUF

notforu777 updated a model about 8 hours ago

AtomicChat/FLUX-3-Image-Klein-pup-GGUF

View all activity

AtomicChat 's collections 45

FLUX 3 Image Klein Uncensored

FLUX 3 Image Klein's text encoder and prompt upsampler without refusals, as GGUF, with what they do to the pictures measured.

AtomicChat/FLUX-3-Image-Klein-TE-Uncensored-GGUF

Text-to-Image • 4B • Updated about 8 hours ago • 1
AtomicChat/FLUX-3-Image-Klein-pup-Uncensored-GGUF

Image-Text-to-Text • 9B • Updated about 8 hours ago • 1
AtomicChat/FLUX-3-Image-Klein-TE-Uncensored-GGUF-metrics

Updated about 8 hours ago • 4
AtomicChat/FLUX-3-Image-Klein-pup-Uncensored-GGUF-metrics

Updated about 8 hours ago • 6

Ornith 1.5 122B Uncensored

AtomicChat/Ornith-1.5-122B-Uncensored-GGUF

Image-Text-to-Text • 125B • Updated about 12 hours ago • 249 • 2

Ornith 1.5

Ornith 1.5 9B, 35B-A3B and 122B quantized to GGUF by AtomicChat, each with its metrics dataset.

AtomicChat/Ornith-1.5-122B-GGUF

Image-Text-to-Text • 125B • Updated about 12 hours ago • 3.1k • 10
AtomicChat/Ornith-1.5-122B-GGUF-metrics

Viewer • Updated about 12 hours ago • 825 • 33
AtomicChat/Ornith-1.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Aug 19 • 21.3k • 63
AtomicChat/Ornith-1.5-35B-A3B-GGUF-metrics

Updated Aug 19 • 378 • 1

Muse Spark Open 816B-A42B

Atomic Dynamic GGUF quants of Meta Muse Spark Open, measured against the other GGUF builds on one stand.

AtomicChat/Muse-Spark-Open-816B-A42B-GGUF

Image-Text-to-Text • 820B • Updated 5 days ago • 554 • 1
AtomicChat/Muse-Spark-Open-816B-A42B-GGUF-metrics

Viewer • Updated 5 days ago • 3.3k • 96

NVIDIA Nemotron 3.5 Super & Bolt GGUF

Atomic Dynamic GGUF quants of Nemotron 3.5 Super VL 120B-A12B and Bolt 74B-A9B, each measured against the other GGUF builds on one stand.

AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF

Image-Text-to-Text • 124B • Updated 5 days ago • 3.43k • 5
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF

Image-Text-to-Text • 74B • Updated 5 days ago • 7.62k • 7
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF-metrics

Viewer • Updated 5 days ago • 697 • 101
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF-metrics

Viewer • Updated 5 days ago • 616 • 93

Ling 3.1 Flash Uncensored

Uncensored builds of Ling 3.1 Flash: refusal direction removed, measured for MMLU and drift.

AtomicChat/Ling-3.1-flash-Uncensored-GGUF

Text Generation • 564B • Updated 7 days ago • 337 • 3
AtomicChat/Ling-3.1-flash-Uncensored-GGUF-metrics

Updated 5 days ago • 36

LFM2.5 24B A2B Uncensored

LFM2.5-24B-A2B without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF

Text Generation • 24B • Updated 8 days ago • 46.9k • 64
AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF-metrics

Updated 8 days ago • 138

MiniCPM-V 4.7 35B A3B Uncensored

MiniCPM-V-4.7-35B-A3B without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF

Image-Text-to-Text • 26.6M • Updated 8 days ago • 8.41k • 39
AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF-metrics

Viewer • Updated 9 days ago • 1.93k • 124

Qwen-Image 2.1 Turbo Uncensored

Qwen-Image's text encoder (Qwen3-VL-8B) with the refusal direction removed, a drop-in --llm for sd.cpp, and what it does to images.

AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF

Text-to-Image • 8B • Updated 8 days ago • 444k • 591
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF-metrics

Viewer • Updated 12 days ago • 432 • 3.42k

Qwen3.8 Flash Next Uncensored

Qwen3.8-Flash-Next without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/Qwen3.8-Flash-Next-Uncensored-GGUF

Text Generation • 79.5M • Updated 8 days ago • 4.85k • 9
AtomicChat/Qwen3.8-Flash-Next-Uncensored-GGUF-metrics

Updated 8 days ago • 388

EmbeddingGemma 2

Google's multimodal embedding model in GGUF: measured AD quants, projector, and the metrics behind them.

AtomicChat/embeddinggemma-2-GGUF

Feature Extraction • 0.3B • Updated 14 days ago • 2.56k • 2
AtomicChat/embeddinggemma-2-GGUF-metrics

Updated 14 days ago • 418

Qwen3.8 Flash Next

Qwen3.8-Flash-Next (177B MoE) in GGUF: measured AD quants and the metrics behind them.

AtomicChat/Qwen3.8-Flash-Next-GGUF

Text Generation • 177B • Updated 1 day ago • 656k • 196
AtomicChat/Qwen3.8-Flash-Next-GGUF-metrics

Viewer • Updated Aug 26 • 5 • 242

Ornith 1.5 35B A3B

AtomicChat/Ornith-1.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Aug 19 • 21.3k • 63
AtomicChat/Ornith-1.5-35B-A3B-GGUF-metrics

Updated Aug 19 • 378 • 1

Nemotron 3.5 Lightning 30B A3B

AtomicChat/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

Text Generation • 33B • Updated Aug 12 • 11.4k • 11
AtomicChat/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF-metrics

Updated Aug 14 • 93

Ling 3.0 Flash

AtomicChat/Ling-3.0-flash-GGUF

Text Generation • 124B • Updated 1 day ago • 229k • 67
AtomicChat/Ling-3.0-flash-GGUF-metrics

Updated Aug 5 • 194
AtomicChat/Ling-3.0-flash-NVFP4-GGUF

Text Generation • 124B • Updated Aug 5 • 85 • 5
AtomicChat/Ling-3.0-flash-NVFP4

Text Generation • 73B • Updated Aug 7 • 145 • 5

Kimi K3

AtomicChat/Kimi-K3

Image-Text-to-Text • 1.5T • Updated Jul 27 • 24 • 1
AtomicChat/Kimi-K3-GGUF

Image-Text-to-Text • 2.8T • Updated Jul 31 • 2.11k • 16

Laguna S 2.1

AtomicChat/Laguna-S-2.1-GGUF

Text Generation • 118B • Updated Jul 22 • 863 • 11
AtomicChat/Laguna-S-2.1-MLX-4bit

Text Generation • 118B • Updated Jul 22 • 153 • 1
AtomicChat/Laguna-S-2.1-MLX-8bit

Text Generation • 118B • Updated Jul 22 • 62
AtomicChat/Laguna-S-2.1-NVFP4

Text Generation • 66B • Updated Jul 22 • 36 • 2

Hy3

Atomic Chat GGUF builds of Tencent Hy3 (295B MoE): coding-optimized imatrix quants

AtomicChat/Hy3-GGUF

Text Generation • 299B • Updated Jul 22 • 127 • 5

Laguna XS 2.1

poolside Laguna XS 2.1 (33B/3B MoE) quantized by Atomic Chat - GGUF (llama.cpp) and MLX (Apple Silicon) ladders.

AtomicChat/Laguna-XS-2.1-GGUF

Text Generation • 33B • Updated Jul 22 • 1.53k • 17
AtomicChat/Laguna-XS-2.1-MLX-8bit

Text Generation • 33B • Updated Jul 22 • 504 • 2
AtomicChat/Laguna-XS-2.1-MLX-6bit

Text Generation • 33B • Updated Jul 22 • 157 • 2
AtomicChat/Laguna-XS-2.1-MLX-5bit

Text Generation • 33B • Updated Jul 22 • 264 • 3

Qwen 2.5

Qwen2.5 instruct models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix.

AtomicChat/Qwen2.5-7B-Instruct-GGUF

Text Generation • 8B • Updated Jul 22 • 626 • 1
AtomicChat/Qwen2.5-14B-Instruct-GGUF

Text Generation • 15B • Updated Jul 22 • 192 • 2

Ornith 1.0

DeepReinforce's Ornith 1.0 agentic-coding models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix. Runs fully offline.

AtomicChat/Ornith-9B-GGUF

Text Generation • 9B • Updated Jul 22 • 610 • 15
AtomicChat/Ornith-35B-GGUF

Text Generation • 35B • Updated Jul 22 • 354 • 8
AtomicChat/Ornith-9B-MLX-4bit

Text Generation • 9B • Updated Jul 22 • 75
AtomicChat/Ornith-9B-MLX-5bit

Text Generation • 9B • Updated Jul 22 • 146 • 1

Qwen Coder

Atomic Chat self-quantized GGUFs of the Qwen3 Coder models, built from the original weights with an importance matrix.

AtomicChat/Qwen3-Coder-30B-A3B-GGUF

Text Generation • 31B • Updated Jul 22 • 6.42k • 4

Gemma 4 Assistant GGUF

Gemma 4 MTP assistant drafters as GGUF (F16/Q8_0/Q5_K_M/Q4_K_M/Q4_K_S). Speculative-decoding heads for the atomic-llama-cpp-turboquant fork.

AtomicChat/gemma-4-E2B-it-assistant-GGUF

Text Generation • 77.2M • Updated Jul 23 • 1.27k • 8
AtomicChat/gemma-4-E4B-it-assistant-GGUF

Text Generation • 78M • Updated Jul 23 • 1.6k • 26
AtomicChat/gemma-4-26B-A4B-it-assistant-GGUF

Text Generation • 0.4B • Updated Jul 23 • 2.62k • 33
AtomicChat/gemma-4-31B-it-assistant-GGUF

Text Generation • 0.5B • Updated Jul 23 • 1.87k • 22

FLUX 3 Image Klein

BFL's 16-step image and edit model in GGUF: measured AD quants, text encoder, prompt upsampler, and the renders behind them.

AtomicChat/FLUX-3-Image-Klein-GGUF

Text-to-Image • 6B • Updated about 8 hours ago • 2
AtomicChat/FLUX-3-Image-Klein-pup-GGUF

Image-Text-to-Text • 9B • Updated about 8 hours ago
AtomicChat/FLUX-3-Image-Klein-GGUF-metrics

Viewer • Updated about 9 hours ago • 96
AtomicChat/FLUX-3-Image-Klein-pup-GGUF-metrics

Updated about 23 hours ago

DeepSeek-V4.1-Flash-1017 Uncensored

DeepSeek-V4.1-Flash-1017 without refusals: GGUF builds, the adapter and their measurements

AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF

Text Generation • 0.1B • Updated 1 day ago • 132 • 29
AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics

Viewer • Updated about 9 hours ago • 1.93k • 73
AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-DwarfStar-GGUF

Text Generation • 755B • Updated about 7 hours ago

Beam 1.0 501B-A23B

Atomic Dynamic GGUF quants of Reflection Beam 1.0 (501B-A23B MoE), measured against the other GGUF builds on one stand.

AtomicChat/Beam-1.0-501B-A23B-GGUF

Text Generation • 501B • Updated 5 days ago • 207 • 3
AtomicChat/Beam-1.0-501B-A23B-GGUF-metrics

Viewer • Updated 5 days ago • 341k • 110

NVIDIA Nemotron 3.5 Uncensored

Nemotron 3.5 Super VL and Bolt with the refusal direction projected out, baked into Atomic Dynamic GGUF builds.

AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF

Image-Text-to-Text • 124B • Updated 6 days ago • 1.35k • 5
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF

Image-Text-to-Text • 74B • Updated 5 days ago • 8.76k • 11
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF-metrics

Viewer • Updated 5 days ago • 1.93k • 638
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF-metrics

Viewer • Updated 5 days ago • 1.93k • 742

Ternary Bonsai 2 Uncensored

Ternary Bonsai 2 without refusals: rank-1 LoRA adapters for PrismML's 2B, 4B, 9B and 27B packs, which stay byte-identical, plus the metrics.

AtomicChat/Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF

Text Generation • 2.42M • Updated 5 days ago • 1.7k • 11
AtomicChat/Ternary-Bonsai-2-9B-Uncensored-LoRA-GGUF

Text Generation • 786k • Updated 5 days ago • 535 • 6
AtomicChat/Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF

Text Generation • 590k • Updated 5 days ago • 215 • 3
AtomicChat/Ternary-Bonsai-2-2B-Uncensored-LoRA-GGUF

Text Generation • 295k • Updated 5 days ago • 202 • 2

Ling 3.1 Flash

Atomic Dynamic GGUF quants of inclusionAI Ling 3.1 Flash, measured against the other GGUF builds on one stand.

AtomicChat/Ling-3.1-flash-GGUF

Text Generation • 564B • Updated 7 days ago • 1.62k • 10
AtomicChat/Ling-3.1-flash-GGUF-metrics

Preview • Updated 5 days ago • 651

LFM2.5

Atomic Chat self-quantized GGUFs of Liquid AI's LFM2.5 models, built from the original weights with an importance matrix.

AtomicChat/LFM2.5-8B-A1B-GGUF

Text Generation • 8B • Updated Jul 22 • 633 • 5
AtomicChat/LFM2.5-24B-A2B-GGUF

Text Generation • 24B • Updated 8 days ago • 2.46k • 7
AtomicChat/LFM2.5-24B-A2B-GGUF-metrics

Viewer • Updated 8 days ago • 3.08k • 124

MiniCPM-V 4.7

OpenBMB's MiniCPM-V 4.7 (35B-A3B MoE and 1B) in GGUF: measured AD quants, projector, and the metrics behind them.

AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 9 days ago • 20k • 17
AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF-metrics

Viewer • Updated 9 days ago • 615 • 159
AtomicChat/MiniCPM-V-4.7-1B-GGUF

Image-Text-to-Text • 1B • Updated 9 days ago • 10.9k • 7
AtomicChat/MiniCPM-V-4.7-1B-GGUF-metrics

Viewer • Updated 9 days ago • 283 • 86

Qwen-Image 2.1 Turbo

Qwen's 8-step image model in GGUF for stable-diffusion.cpp: measured AD quants and the renders behind them.

AtomicChat/Qwen-Image-2.1-Turbo-GGUF

Text-to-Image • 7B • Updated 8 days ago • 166k • 37
AtomicChat/Qwen-Image-2.1-Turbo-GGUF-metrics

Viewer • Updated 12 days ago • 48 • 286

Liquid d1

Liquid AI d1 decision models (d1-3B, d1-omni-600M) in GGUF: measured AD quants and the metrics behind them.

AtomicChat/d1-3B-GGUF

Image-Text-to-Text • 3B • Updated 14 days ago • 2.19k • 12
AtomicChat/d1-3B-GGUF-metrics

Updated 14 days ago • 361
AtomicChat/d1-omni-600M-GGUF

Image-Text-to-Text • 0.4B • Updated 13 days ago • 503
AtomicChat/d1-omni-600M-GGUF-metrics

Updated 13 days ago • 347

DeepSeek V4.1 Flash

NVFP4 experts for Blackwell, calibrated by NVIDIA's recipe and measured against the original: checkpoint plus the metrics.

AtomicChat/DeepSeek-V4.1-Flash-NVFP4-nvidia

Text Generation • 763B • Updated 12 days ago • 279 • 5
AtomicChat/DeepSeek-V4.1-Flash-NVFP4-metrics

Updated Sep 10 • 3.29k • 1

Ornith 1.5 9B

AtomicChat/Ornith-1.5-9B-GGUF

Image-Text-to-Text • 9B • Updated Aug 20 • 49k • 78
AtomicChat/Ornith-1.5-9B-GGUF-metrics

Viewer • Updated Aug 19 • 48 • 189 • 1

Qwen 3.8 27B

AtomicChat/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Aug 18 • 57.2k • 178
AtomicChat/Qwen3.8-27B-GGUF-metrics

Updated Aug 21 • 2.43k • 4
AtomicChat/Qwen3.8-27B-MLX-AD-3.50bpw-DWQ-12.7GB

Image-Text-to-Text • 27B • Updated Aug 25 • 235 • 2
AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB

Image-Text-to-Text • 27B • Updated Aug 25 • 327 • 3

Muse Glimmer 30B

AtomicChat/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated Aug 11 • 5.95k • 9
AtomicChat/Muse-Glimmer-30B-GGUF-metrics

Viewer • Updated Aug 11 • 587k • 1.49k

DeepSeek V4 Flash 0731

AtomicChat/DeepSeek-V4-Flash-0731-GGUF

Text Generation • 284B • Updated Aug 4 • 1.28k • 32
AtomicChat/dsv4-eval-artifacts

Viewer • Updated Aug 3 • 50 • 283

Gemma 4

Atomic Chat GGUF builds of Google Gemma 4

AtomicChat/gemma-4-31B-it-GGUF

Image-Text-to-Text • 31B • Updated Jul 24 • 5.76k • 1
AtomicChat/gemma-4-31B-it-NVFP4

Text Generation • 18B • Updated Jul 22 • 68
AtomicChat/gemma-4-31B-it-MLX-4bit

Text Generation • 31B • Updated Jul 22 • 206
AtomicChat/gemma-4-31B-it-MLX-8bit

Text Generation • 31B • Updated Jul 22 • 51

Inkling

Inkling by Thinking Machines, self-quantized to GGUF by Atomic Chat. 975B MoE (41B active), 1M context.

AtomicChat/Inkling-GGUF

Text Generation • 947B • Updated Jul 22 • 189 • 4

DFlash speculative drafts

DFlash block-diffusion draft heads (GGUF). Attach to any target GGUF to speed up llama.cpp.

AtomicChat/Qwen3-4B-DFlash-GGUF

Text Generation • 0.5B • Updated 1 day ago • 40.3k
AtomicChat/Qwen3-8B-DFlash-GGUF

Text Generation • 1B • Updated Jul 22 • 192
AtomicChat/Qwen3.5-4B-DFlash-GGUF

Text Generation • 0.6B • Updated 1 day ago • 40.1k • 1
AtomicChat/Qwen3.5-9B-DFlash-GGUF

Text Generation • 1B • Updated 1 day ago • 39.9k • 2

Qwen 3.6

Atomic Chat self-quantized GGUFs of Qwen3.6, built from the original weights with an importance matrix.

AtomicChat/Qwen3.6-27B-GGUF

Text Generation • 27B • Updated Jul 22 • 4.15k • 1
AtomicChat/Qwen3.6-35B-A3B-GGUF

Text Generation • 35B • Updated Jul 22 • 3.89k • 3

Phi 4

Microsoft Phi-4 models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix.

AtomicChat/Phi-4-mini-instruct-GGUF

Text Generation • 4B • Updated Jul 22 • 894 • 2

Qwen 3.5

Atomic Chat self-quantized GGUFs of Qwen3.5, built from the original weights with an importance matrix.

AtomicChat/Qwen3.5-4B-GGUF

Text Generation • 4B • Updated 1 day ago • 11.2k • 1

Qwen 3.6 UDT MTP

Dynamic-imatrix GGUF quants of Qwen 3.6 27B & 35B-A3B. TurboQuant3 KV + shared-model NextN ready.

AtomicChat/Qwen3.6-27B-UDT-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated Jul 22 • 531 • 10
AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF

Image-Text-to-Text • 0.4B • Updated Jul 22 • 5.35k • 13

FLUX 3 Image Klein Uncensored

FLUX 3 Image Klein's text encoder and prompt upsampler without refusals, as GGUF, with what they do to the pictures measured.

AtomicChat/FLUX-3-Image-Klein-TE-Uncensored-GGUF

Text-to-Image • 4B • Updated about 8 hours ago • 1
AtomicChat/FLUX-3-Image-Klein-pup-Uncensored-GGUF

Image-Text-to-Text • 9B • Updated about 8 hours ago • 1
AtomicChat/FLUX-3-Image-Klein-TE-Uncensored-GGUF-metrics

Updated about 8 hours ago • 4
AtomicChat/FLUX-3-Image-Klein-pup-Uncensored-GGUF-metrics

Updated about 8 hours ago • 6

FLUX 3 Image Klein

BFL's 16-step image and edit model in GGUF: measured AD quants, text encoder, prompt upsampler, and the renders behind them.

AtomicChat/FLUX-3-Image-Klein-GGUF

Text-to-Image • 6B • Updated about 8 hours ago • 2
AtomicChat/FLUX-3-Image-Klein-pup-GGUF

Image-Text-to-Text • 9B • Updated about 8 hours ago
AtomicChat/FLUX-3-Image-Klein-GGUF-metrics

Viewer • Updated about 9 hours ago • 96
AtomicChat/FLUX-3-Image-Klein-pup-GGUF-metrics

Updated about 23 hours ago

Ornith 1.5 122B Uncensored

AtomicChat/Ornith-1.5-122B-Uncensored-GGUF

Image-Text-to-Text • 125B • Updated about 12 hours ago • 249 • 2

DeepSeek-V4.1-Flash-1017 Uncensored

DeepSeek-V4.1-Flash-1017 without refusals: GGUF builds, the adapter and their measurements

AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF

Text Generation • 0.1B • Updated 1 day ago • 132 • 29
AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics

Viewer • Updated about 9 hours ago • 1.93k • 73
AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-DwarfStar-GGUF

Text Generation • 755B • Updated about 7 hours ago

Ornith 1.5

Ornith 1.5 9B, 35B-A3B and 122B quantized to GGUF by AtomicChat, each with its metrics dataset.

AtomicChat/Ornith-1.5-122B-GGUF

Image-Text-to-Text • 125B • Updated about 12 hours ago • 3.1k • 10
AtomicChat/Ornith-1.5-122B-GGUF-metrics

Viewer • Updated about 12 hours ago • 825 • 33
AtomicChat/Ornith-1.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Aug 19 • 21.3k • 63
AtomicChat/Ornith-1.5-35B-A3B-GGUF-metrics

Updated Aug 19 • 378 • 1

Beam 1.0 501B-A23B

Atomic Dynamic GGUF quants of Reflection Beam 1.0 (501B-A23B MoE), measured against the other GGUF builds on one stand.

AtomicChat/Beam-1.0-501B-A23B-GGUF

Text Generation • 501B • Updated 5 days ago • 207 • 3
AtomicChat/Beam-1.0-501B-A23B-GGUF-metrics

Viewer • Updated 5 days ago • 341k • 110

Muse Spark Open 816B-A42B

Atomic Dynamic GGUF quants of Meta Muse Spark Open, measured against the other GGUF builds on one stand.

AtomicChat/Muse-Spark-Open-816B-A42B-GGUF

Image-Text-to-Text • 820B • Updated 5 days ago • 554 • 1
AtomicChat/Muse-Spark-Open-816B-A42B-GGUF-metrics

Viewer • Updated 5 days ago • 3.3k • 96

NVIDIA Nemotron 3.5 Uncensored

Nemotron 3.5 Super VL and Bolt with the refusal direction projected out, baked into Atomic Dynamic GGUF builds.

AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF

Image-Text-to-Text • 124B • Updated 6 days ago • 1.35k • 5
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF

Image-Text-to-Text • 74B • Updated 5 days ago • 8.76k • 11
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF-metrics

Viewer • Updated 5 days ago • 1.93k • 638
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF-metrics

Viewer • Updated 5 days ago • 1.93k • 742

NVIDIA Nemotron 3.5 Super & Bolt GGUF

Atomic Dynamic GGUF quants of Nemotron 3.5 Super VL 120B-A12B and Bolt 74B-A9B, each measured against the other GGUF builds on one stand.

AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF

Image-Text-to-Text • 124B • Updated 5 days ago • 3.43k • 5
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF

Image-Text-to-Text • 74B • Updated 5 days ago • 7.62k • 7
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF-metrics

Viewer • Updated 5 days ago • 697 • 101
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF-metrics

Viewer • Updated 5 days ago • 616 • 93

Ternary Bonsai 2 Uncensored

Ternary Bonsai 2 without refusals: rank-1 LoRA adapters for PrismML's 2B, 4B, 9B and 27B packs, which stay byte-identical, plus the metrics.

AtomicChat/Ternary-Bonsai-2-27B-Uncensored-LoRA-GGUF

Text Generation • 2.42M • Updated 5 days ago • 1.7k • 11
AtomicChat/Ternary-Bonsai-2-9B-Uncensored-LoRA-GGUF

Text Generation • 786k • Updated 5 days ago • 535 • 6
AtomicChat/Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF

Text Generation • 590k • Updated 5 days ago • 215 • 3
AtomicChat/Ternary-Bonsai-2-2B-Uncensored-LoRA-GGUF

Text Generation • 295k • Updated 5 days ago • 202 • 2

Ling 3.1 Flash Uncensored

Uncensored builds of Ling 3.1 Flash: refusal direction removed, measured for MMLU and drift.

AtomicChat/Ling-3.1-flash-Uncensored-GGUF

Text Generation • 564B • Updated 7 days ago • 337 • 3
AtomicChat/Ling-3.1-flash-Uncensored-GGUF-metrics

Updated 5 days ago • 36

Ling 3.1 Flash

Atomic Dynamic GGUF quants of inclusionAI Ling 3.1 Flash, measured against the other GGUF builds on one stand.

AtomicChat/Ling-3.1-flash-GGUF

Text Generation • 564B • Updated 7 days ago • 1.62k • 10
AtomicChat/Ling-3.1-flash-GGUF-metrics

Preview • Updated 5 days ago • 651

LFM2.5 24B A2B Uncensored

LFM2.5-24B-A2B without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF

Text Generation • 24B • Updated 8 days ago • 46.9k • 64
AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF-metrics

Updated 8 days ago • 138

LFM2.5

Atomic Chat self-quantized GGUFs of Liquid AI's LFM2.5 models, built from the original weights with an importance matrix.

AtomicChat/LFM2.5-8B-A1B-GGUF

Text Generation • 8B • Updated Jul 22 • 633 • 5
AtomicChat/LFM2.5-24B-A2B-GGUF

Text Generation • 24B • Updated 8 days ago • 2.46k • 7
AtomicChat/LFM2.5-24B-A2B-GGUF-metrics

Viewer • Updated 8 days ago • 3.08k • 124

MiniCPM-V 4.7 35B A3B Uncensored

MiniCPM-V-4.7-35B-A3B without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF

Image-Text-to-Text • 26.6M • Updated 8 days ago • 8.41k • 39
AtomicChat/MiniCPM-V-4.7-35B-A3B-Uncensored-GGUF-metrics

Viewer • Updated 9 days ago • 1.93k • 124

MiniCPM-V 4.7

OpenBMB's MiniCPM-V 4.7 (35B-A3B MoE and 1B) in GGUF: measured AD quants, projector, and the metrics behind them.

AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 9 days ago • 20k • 17
AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF-metrics

Viewer • Updated 9 days ago • 615 • 159
AtomicChat/MiniCPM-V-4.7-1B-GGUF

Image-Text-to-Text • 1B • Updated 9 days ago • 10.9k • 7
AtomicChat/MiniCPM-V-4.7-1B-GGUF-metrics

Viewer • Updated 9 days ago • 283 • 86

Qwen-Image 2.1 Turbo Uncensored

Qwen-Image's text encoder (Qwen3-VL-8B) with the refusal direction removed, a drop-in --llm for sd.cpp, and what it does to images.

AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF

Text-to-Image • 8B • Updated 8 days ago • 444k • 591
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF-metrics

Viewer • Updated 12 days ago • 432 • 3.42k

Qwen-Image 2.1 Turbo

Qwen's 8-step image model in GGUF for stable-diffusion.cpp: measured AD quants and the renders behind them.

AtomicChat/Qwen-Image-2.1-Turbo-GGUF

Text-to-Image • 7B • Updated 8 days ago • 166k • 37
AtomicChat/Qwen-Image-2.1-Turbo-GGUF-metrics

Viewer • Updated 12 days ago • 48 • 286

Qwen3.8 Flash Next Uncensored

Qwen3.8-Flash-Next without refusals: baked GGUF builds and a LoRA adapter for our original quants, plus the metrics.

AtomicChat/Qwen3.8-Flash-Next-Uncensored-GGUF

Text Generation • 79.5M • Updated 8 days ago • 4.85k • 9
AtomicChat/Qwen3.8-Flash-Next-Uncensored-GGUF-metrics

Updated 8 days ago • 388

Liquid d1

Liquid AI d1 decision models (d1-3B, d1-omni-600M) in GGUF: measured AD quants and the metrics behind them.

AtomicChat/d1-3B-GGUF

Image-Text-to-Text • 3B • Updated 14 days ago • 2.19k • 12
AtomicChat/d1-3B-GGUF-metrics

Updated 14 days ago • 361
AtomicChat/d1-omni-600M-GGUF

Image-Text-to-Text • 0.4B • Updated 13 days ago • 503
AtomicChat/d1-omni-600M-GGUF-metrics

Updated 13 days ago • 347

EmbeddingGemma 2

Google's multimodal embedding model in GGUF: measured AD quants, projector, and the metrics behind them.

AtomicChat/embeddinggemma-2-GGUF

Feature Extraction • 0.3B • Updated 14 days ago • 2.56k • 2
AtomicChat/embeddinggemma-2-GGUF-metrics

Updated 14 days ago • 418

DeepSeek V4.1 Flash

NVFP4 experts for Blackwell, calibrated by NVIDIA's recipe and measured against the original: checkpoint plus the metrics.

AtomicChat/DeepSeek-V4.1-Flash-NVFP4-nvidia

Text Generation • 763B • Updated 12 days ago • 279 • 5
AtomicChat/DeepSeek-V4.1-Flash-NVFP4-metrics

Updated Sep 10 • 3.29k • 1

Qwen3.8 Flash Next

Qwen3.8-Flash-Next (177B MoE) in GGUF: measured AD quants and the metrics behind them.

AtomicChat/Qwen3.8-Flash-Next-GGUF

Text Generation • 177B • Updated 1 day ago • 656k • 196
AtomicChat/Qwen3.8-Flash-Next-GGUF-metrics

Viewer • Updated Aug 26 • 5 • 242

Ornith 1.5 9B

AtomicChat/Ornith-1.5-9B-GGUF

Image-Text-to-Text • 9B • Updated Aug 20 • 49k • 78
AtomicChat/Ornith-1.5-9B-GGUF-metrics

Viewer • Updated Aug 19 • 48 • 189 • 1

Ornith 1.5 35B A3B

AtomicChat/Ornith-1.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Aug 19 • 21.3k • 63
AtomicChat/Ornith-1.5-35B-A3B-GGUF-metrics

Updated Aug 19 • 378 • 1

Qwen 3.8 27B

AtomicChat/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Aug 18 • 57.2k • 178
AtomicChat/Qwen3.8-27B-GGUF-metrics

Updated Aug 21 • 2.43k • 4
AtomicChat/Qwen3.8-27B-MLX-AD-3.50bpw-DWQ-12.7GB

Image-Text-to-Text • 27B • Updated Aug 25 • 235 • 2
AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB

Image-Text-to-Text • 27B • Updated Aug 25 • 327 • 3

Nemotron 3.5 Lightning 30B A3B

AtomicChat/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

Text Generation • 33B • Updated Aug 12 • 11.4k • 11
AtomicChat/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF-metrics

Updated Aug 14 • 93

Muse Glimmer 30B

AtomicChat/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated Aug 11 • 5.95k • 9
AtomicChat/Muse-Glimmer-30B-GGUF-metrics

Viewer • Updated Aug 11 • 587k • 1.49k

Ling 3.0 Flash

AtomicChat/Ling-3.0-flash-GGUF

Text Generation • 124B • Updated 1 day ago • 229k • 67
AtomicChat/Ling-3.0-flash-GGUF-metrics

Updated Aug 5 • 194
AtomicChat/Ling-3.0-flash-NVFP4-GGUF

Text Generation • 124B • Updated Aug 5 • 85 • 5
AtomicChat/Ling-3.0-flash-NVFP4

Text Generation • 73B • Updated Aug 7 • 145 • 5

DeepSeek V4 Flash 0731

AtomicChat/DeepSeek-V4-Flash-0731-GGUF

Text Generation • 284B • Updated Aug 4 • 1.28k • 32
AtomicChat/dsv4-eval-artifacts

Viewer • Updated Aug 3 • 50 • 283

Kimi K3

AtomicChat/Kimi-K3

Image-Text-to-Text • 1.5T • Updated Jul 27 • 24 • 1
AtomicChat/Kimi-K3-GGUF

Image-Text-to-Text • 2.8T • Updated Jul 31 • 2.11k • 16

Gemma 4

Atomic Chat GGUF builds of Google Gemma 4

AtomicChat/gemma-4-31B-it-GGUF

Image-Text-to-Text • 31B • Updated Jul 24 • 5.76k • 1
AtomicChat/gemma-4-31B-it-NVFP4

Text Generation • 18B • Updated Jul 22 • 68
AtomicChat/gemma-4-31B-it-MLX-4bit

Text Generation • 31B • Updated Jul 22 • 206
AtomicChat/gemma-4-31B-it-MLX-8bit

Text Generation • 31B • Updated Jul 22 • 51

Laguna S 2.1

AtomicChat/Laguna-S-2.1-GGUF

Text Generation • 118B • Updated Jul 22 • 863 • 11
AtomicChat/Laguna-S-2.1-MLX-4bit

Text Generation • 118B • Updated Jul 22 • 153 • 1
AtomicChat/Laguna-S-2.1-MLX-8bit

Text Generation • 118B • Updated Jul 22 • 62
AtomicChat/Laguna-S-2.1-NVFP4

Text Generation • 66B • Updated Jul 22 • 36 • 2

Inkling

Inkling by Thinking Machines, self-quantized to GGUF by Atomic Chat. 975B MoE (41B active), 1M context.

AtomicChat/Inkling-GGUF

Text Generation • 947B • Updated Jul 22 • 189 • 4

Hy3

Atomic Chat GGUF builds of Tencent Hy3 (295B MoE): coding-optimized imatrix quants

AtomicChat/Hy3-GGUF

Text Generation • 299B • Updated Jul 22 • 127 • 5

DFlash speculative drafts

DFlash block-diffusion draft heads (GGUF). Attach to any target GGUF to speed up llama.cpp.

AtomicChat/Qwen3-4B-DFlash-GGUF

Text Generation • 0.5B • Updated 1 day ago • 40.3k
AtomicChat/Qwen3-8B-DFlash-GGUF

Text Generation • 1B • Updated Jul 22 • 192
AtomicChat/Qwen3.5-4B-DFlash-GGUF

Text Generation • 0.6B • Updated 1 day ago • 40.1k • 1
AtomicChat/Qwen3.5-9B-DFlash-GGUF

Text Generation • 1B • Updated 1 day ago • 39.9k • 2

Laguna XS 2.1

poolside Laguna XS 2.1 (33B/3B MoE) quantized by Atomic Chat - GGUF (llama.cpp) and MLX (Apple Silicon) ladders.

AtomicChat/Laguna-XS-2.1-GGUF

Text Generation • 33B • Updated Jul 22 • 1.53k • 17
AtomicChat/Laguna-XS-2.1-MLX-8bit

Text Generation • 33B • Updated Jul 22 • 504 • 2
AtomicChat/Laguna-XS-2.1-MLX-6bit

Text Generation • 33B • Updated Jul 22 • 157 • 2
AtomicChat/Laguna-XS-2.1-MLX-5bit

Text Generation • 33B • Updated Jul 22 • 264 • 3

Qwen 3.6

Atomic Chat self-quantized GGUFs of Qwen3.6, built from the original weights with an importance matrix.

AtomicChat/Qwen3.6-27B-GGUF

Text Generation • 27B • Updated Jul 22 • 4.15k • 1
AtomicChat/Qwen3.6-35B-A3B-GGUF

Text Generation • 35B • Updated Jul 22 • 3.89k • 3

Qwen 2.5

Qwen2.5 instruct models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix.

AtomicChat/Qwen2.5-7B-Instruct-GGUF

Text Generation • 8B • Updated Jul 22 • 626 • 1
AtomicChat/Qwen2.5-14B-Instruct-GGUF

Text Generation • 15B • Updated Jul 22 • 192 • 2

Phi 4

Microsoft Phi-4 models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix.

AtomicChat/Phi-4-mini-instruct-GGUF

Text Generation • 4B • Updated Jul 22 • 894 • 2

Ornith 1.0

DeepReinforce's Ornith 1.0 agentic-coding models, self-quantized to GGUF by Atomic Chat with a per-tensor importance matrix. Runs fully offline.

AtomicChat/Ornith-9B-GGUF

Text Generation • 9B • Updated Jul 22 • 610 • 15
AtomicChat/Ornith-35B-GGUF

Text Generation • 35B • Updated Jul 22 • 354 • 8
AtomicChat/Ornith-9B-MLX-4bit

Text Generation • 9B • Updated Jul 22 • 75
AtomicChat/Ornith-9B-MLX-5bit

Text Generation • 9B • Updated Jul 22 • 146 • 1

Qwen 3.5

Atomic Chat self-quantized GGUFs of Qwen3.5, built from the original weights with an importance matrix.

AtomicChat/Qwen3.5-4B-GGUF

Text Generation • 4B • Updated 1 day ago • 11.2k • 1

Qwen Coder

Atomic Chat self-quantized GGUFs of the Qwen3 Coder models, built from the original weights with an importance matrix.

AtomicChat/Qwen3-Coder-30B-A3B-GGUF

Text Generation • 31B • Updated Jul 22 • 6.42k • 4

Qwen 3.6 UDT MTP

Dynamic-imatrix GGUF quants of Qwen 3.6 27B & 35B-A3B. TurboQuant3 KV + shared-model NextN ready.

AtomicChat/Qwen3.6-27B-UDT-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated Jul 22 • 531 • 10
AtomicChat/Qwen3.6-35B-A3B-UDT-MTP-GGUF

Image-Text-to-Text • 0.4B • Updated Jul 22 • 5.35k • 13

Gemma 4 Assistant GGUF

Gemma 4 MTP assistant drafters as GGUF (F16/Q8_0/Q5_K_M/Q4_K_M/Q4_K_S). Speculative-decoding heads for the atomic-llama-cpp-turboquant fork.

AtomicChat/gemma-4-E2B-it-assistant-GGUF

Text Generation • 77.2M • Updated Jul 23 • 1.27k • 8
AtomicChat/gemma-4-E4B-it-assistant-GGUF

Text Generation • 78M • Updated Jul 23 • 1.6k • 26
AtomicChat/gemma-4-26B-A4B-it-assistant-GGUF

Text Generation • 0.4B • Updated Jul 23 • 2.62k • 33
AtomicChat/gemma-4-31B-it-assistant-GGUF

Text Generation • 0.5B • Updated Jul 23 • 1.87k • 22

AI & ML interests

Recent Activity

Team members 6

AtomicChat 's collections 45