NVIDIA releases official NVFP4 quantization of Qwen 3.8 27B

llm_wizard · x · 2026-09-09

NVIDIA AI confirmed the release of an NVFP4 quantized version of Qwen 3.8 27B, now available on Hugging Face. NVFP4 is NVIDIA's 4-bit floating-point format that shrinks model size and boosts inference efficiency while retaining accuracy, making the Qwen model easier to run locally on RTX and data center GPUs.

Related event: NVIDIA releases official NVFP4 quantized Qwen3.8-27B(2 posts)→

Original post →

More from Infra

Infra channel →