Fast inference for Blackwell GPUs
AI & ML interests
None defined yet.
Recent Activity
Quantizations of the Qwen3.5 familly
-
ig1/Qwen2.5-VL-7B-Instruct-NVFP4
Image-Text-to-Text • 5B • Updated • 1 -
ig1/Qwen2.5-VL-7B-Instruct-FP8-Dynamic
Image-Text-to-Text • 8B • Updated • 1 -
ig1/Qwen2.5-VL-32B-Instruct-FP8-Dynamic
Image-Text-to-Text • 33B • Updated • 1 -
ig1/Qwen2.5-VL-72B-Instruct-FP8-Dynamic
Image-Text-to-Text • 73B • Updated • 1.17k
Fast inference for Blackwell GPUs
Quantizations of the Qwen3.5 familly
Quantizations of the Qwen3 familly
-
ig1/Qwen2.5-VL-7B-Instruct-NVFP4
Image-Text-to-Text • 5B • Updated • 1 -
ig1/Qwen2.5-VL-7B-Instruct-FP8-Dynamic
Image-Text-to-Text • 8B • Updated • 1 -
ig1/Qwen2.5-VL-32B-Instruct-FP8-Dynamic
Image-Text-to-Text • 33B • Updated • 1 -
ig1/Qwen2.5-VL-72B-Instruct-FP8-Dynamic
Image-Text-to-Text • 73B • Updated • 1.17k