torchao INT8/FP8 weight-only quantized MiniMax-H3 (video+audio omni) for consumer GPUs. Group-offload recipe; load with diffusers (main) + torchao.
Chohan
abhishekchohan
AI & ML interests
None yet
Recent Activity
updated a model 5 days ago
abhishekchohan/Qwen3.8-27B-GPTQ-INT4 published a model 5 days ago
abhishekchohan/Qwen3.8-27B-GPTQ-INT4 updated a model 8 days ago
abhishekchohan/Muse-Glimmer-30B-GPTQ-INT4Organizations
None yet
models 83
abhishekchohan/Qwen3.8-27B-GPTQ-INT4
Image-Text-to-Text • 28B • Updated • 434
abhishekchohan/Muse-Glimmer-30B-GPTQ-INT4
Image-Text-to-Text • 9B • Updated • 285 • 2
abhishekchohan/minimax-h3-fp8
Text-to-Video • Updated • 57
abhishekchohan/minimax-h3-int8
Text-to-Video • Updated • 120 • 1
abhishekchohan/flux2-klein-4b-fp8
Text-to-Image • Updated • 60
abhishekchohan/flux2-klein-9b-fp8
Text-to-Image • Updated • 49
abhishekchohan/maesar-9B-v2
9B • Updated • 151
abhishekchohan/gemma-4-E4B-it-W4A16
9B • Updated • 189
abhishekchohan/Qwen3.6-35B-A3B-Abliterated-AWQ
36B • Updated • 4.23k • 2
abhishekchohan/gemma-4-26B-A4B-it-abliterated-AWQ
27B • Updated • 1.35k • 1
datasets 0
None public yet