nvfp4-quantization

Tag

Cards List
#nvfp4-quantization

@Ex0byt: Days of model activations, slicing, splicing, fine-tuning + 15 hours of nail-biting NVFP4 calibration/propagation passe…

X AI KOLs Following · 2026-04-22 Cached

A community member released Qwen3.6-35B-A3B-PRISM-NVFP4, a multi-pass, dataset-calibrated zero-loss NVFP4 quantized variant of the Qwen model.

0 favorites 0 likes
#nvfp4-quantization

RedHatAI/Qwen3.6-35B-A3B-NVFP4

Hugging Face Models Trending · 2026-04-17 Cached

Red Hat AI released an NVFP4-quantized 35B MoE version of Qwen3.6 that retains 96.28% GSM8K accuracy while enabling 4-bit inference via vLLM.

0 favorites 0 likes
← Back to home

Submit Feedback