NVIDIA releases NVFP4-quantized Qwen3.6-35B checkpoint on Hugging Face

4-bit NVFP4 build of Alibaba’s Qwen3.6-35B-A3B lands with Apache-2.0 license, long-context support, and vLLM instructions; NVIDIA notes it did not develop the base model.

By · Published

Primary source: Hugging Face

Why it matters

Pre-quantized, permissively licensed checkpoints reduce the time and cost to get a capable long-context MoE model into production, especially for vLLM users on Hopper and Blackwell GPUs.

Illustration of NVIDIA releasing an NVFP4-quantized Qwen3.6-35B checkpoint for Alibaba's Qwen3.6-35B-A3B being published to Hugging Face.

NVIDIA published a quantized version of Alibaba's Qwen3.6-35B-A3B model on Hugging Face on May 28th, 2026, packaged as Qwen3.6-35B-A3B-NVFP4 under the Apache-2.0 license. NVIDIA stresses the underlying model is third-party and not developed by NVIDIA; this release applies NVIDIA's quantization for deployment.…

Reader comments

Conversation for this story loads after sign-in.