NVIDIA ships NVFP4-quantized Qwen3.8-27B, trending on Hugging Face

nvidia · hf · 2026-09-11

NVIDIA released an NVFP4-quantized version of Qwen3.8-27B on Hugging Face, now trending on the model leaderboard. It was produced with the Model Optimizer (ModelOpt) pipeline, ships as safetensors, targets FP4 precision with FP8-related tags for inference cost optimization, and works out of the box with the text-generation pipeline.

Related event: Nvidia Releases NVFP4 Quantized Qwen3.8-27B, Tops Hugging Face Trending(3 posts)→

Original post →

More from Infra

Infra channel →