Hugging Face's logo

RadixArk
/
Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text
Safetensors
Model Optimizer
qwen4_exp
ModelOpt
Qwen3.8
quantized
FP4
fp4
sglang
conversational
8-bit precision
modelopt
Model card Files
xet
 Community
4
Qwen3.8-Flash-Next-NVFP4 / hf_quant_config.json

Commit History

Qwen3.8-Flash-Next-NVFP4: NVFP4 routed experts + FP8 PLE (135GB)
7b71922

justintong commited on