Hugging Face's logo

et0dev
/
Qwen3.5-122B-A10B-NVFP4-Full-GB10

Image-Text-to-Text
Safetensors
qwen3_5_moe
nvfp4
compressed-tensors
quantized
vllm
dgx-spark
gb10
Mixture of Experts
conversational
8-bit precision
Model card Files
xet
 Community
Qwen3.5-122B-A10B-NVFP4-Full-GB10 / tokenizer.json

Commit History

NVFP4-only quant v2 (all Linear incl MTP → NVFP4)
496733f
verified

demon-zombie commited on