Hugging Face's logo

daavidhauser
/
Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen-INT4

Text Generation
Safetensors
vllm
qwen3_5
compressed-tensors
awq
hyperqwen
efficient-thinking
gptq
conversational
Model card Files
xet
 Community
Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen-INT4 / preprocessor_config.json

Commit History

Release Swift 1.5 HyperQwen fast quantization with RTX 3090 evaluation
1613e65
verified

daavidhauser commited on