mgoin/Qwen3-4B-speculator.dflash2
1B • Updated • 292 • 2
Michael Goin
mgoin
AI & ML interests
LLM inference optimization, compression, quantization, pruning, distillation
Recent Activity
updated a model 18 days ago
mgoin/Qwen3-4B-speculator.dflash2 published a model 18 days ago
mgoin/Qwen3-4B-speculator.dflash2 updated a model 25 days ago
mgoin/Qwen3.8-2.4T-A95B-NVFP4-pruned75Organizations
mgoin/Qwen3.8-2.4T-A95B-NVFP4-pruned75
Text Generation • 349B • Updated • 201 • 1
mgoin/Qwen3.8-2.4T-A95B-NVFP4-pruned94
Text Generation • 124B • Updated • 171
mgoin/Kimi-K3-pruned75
Image-Text-to-Text • 737B • Updated • 10.8k
mgoin/Kimi-K3-pruned50
Image-Text-to-Text • 1.4T • Updated • 231 • 1
mgoin/GLM-5.2-speculator.dspark-preview
Text Generation • 4B • Updated • 948 • 61
mgoin/GLM-5.2-speculator.dspark-block16
Text Generation • 4B • Updated • 75 • 2
mgoin/Qwen3-8B-speculator.dspark-reasoning
Text Generation • 2B • Updated • 40
mgoin/Qwen3-8B-speculator.dflash
Text Generation • 2B • Updated • 16
mgoin/Qwen3-8B-speculator.dspark
Text Generation • 2B • Updated • 80
mgoin/Qwen3.6-35B-A3B-2Bit-GSQ-ct
Image-Text-to-Text • 35B • Updated • 8
mgoin/Qwen3-0.6B-MXFP8
0.6B • Updated • 1.63k
mgoin/GLM-4.6-FP8-BLOCK
Text Generation • 357B • Updated • 24
mgoin/Qwen3-0.6B-NVFP4
0.6B • Updated • 54
mgoin/mlperf-inference-llama3.1-8b-data
Updated
mgoin/Llama-3.1-8B-Instruct-FP8-BLOCK
8B • Updated • 4
mgoin/SEMIKONG-70B-W4A16-G128
71B • Updated • 3
mgoin/llama-4-tiny-random
Text Generation • 6.69M • Updated • 7
mgoin/Qwen1.5-14B-Chat-GPTQ
Text Generation • Updated • 9
mgoin/pixtral-12b
Image-Text-to-Text • 13B • Updated • 644 • 1
mgoin/Llama-3.2-1B-Instruct-FP8-ATTN
1B • Updated • 5
mgoin/Llama-3.2-1B-Instruct-FP8-dynamic-ATTN
1B • Updated • 5
mgoin/Pixtral-Large-Instruct-2411
Updated • 2
mgoin/Qwen2.5-Coder-32B-Instruct-fp8
Updated
mgoin/nemotron-3-8b-chat-4k-sft-hf
Text Generation • 9B • Updated • 53
mgoin/llava-onevision-qwen2-7b-ov-hf-bnb-full-4bit
Image-Text-to-Text • 8B • Updated • 9
mgoin/MiniCPM-Llama3-V-2_5-int4
Visual Question Answering • 9B • Updated • 11
mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8
16B • Updated • 30
mgoin/Mixtral-8x7B-Instruct-v0.1-FP8
47B • Updated • 5
mgoin/Nemotron-nemo-checkpoints
Updated