Hugging Face's logo

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

Text Generation
Safetensors
qwen3_5_moe
nvfp4
fp4
llm-compressor
compressed-tensors
vllm
Mixture of Experts
quantized
conversational
8-bit precision
Model card Files
xet
 Community
Qwen3.6-35B-A3B-NVFP4 / chat_template.jinja

Commit History

NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
894cdfa
verified

kyaky commited on