Hugging Face's logo

devan-carlin
/
Qwen3.8-Flash-Next-W4A16

Text Generation
Safetensors
vllm
qwen4_exp
intel-arc
xpu
w4a16
Mixture of Experts
long-context
256k
conversational
compressed-tensors
Model card Files
xet
 Community
Qwen3.8-Flash-Next-W4A16 / preprocessor_config.json

Commit History

Qwen3.8-Flash-Next W4A16 (int4 g128) + PLE table, XPU serving recipe
26ce172
verified

devan-carlin commited on