wtdcode
/

Qwen3.8-Flash-Next-AWQ-W4A16

compressed-tensors

Model card Files Files and versions

Qwen3.8-Flash-Next-AWQ-W4A16 / config.json

Commit History

config: use full_attention layer_type naming for vLLM compatibility

306003e
verified

wtdcode commited on 6 days ago

Add files using upload-large-folder tool

fb5cd79
verified

wtdcode commited on 6 days ago