Back to AIBriefs
LaunchAI Models

NVIDIA releases Qwen3.6-35B-A3B-NVFP4 quantized model

NVIDIA releases Qwen3.6-35B-A3B-NVFP4 quantized modelHugging Face Models

The model uses 35B total parameters with 3B active (A3B) and NVFP4 4-bit floating point quantization. It has gained 46 likes and 67,020 downloads on HuggingFace since release.

·
21 days ago
NVIDIA releases Qwen3.6-35B-A3B-NVFP4 quantized model — AIBriefs