daavidhauser
/

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

Text Generation

compressed-tensors

efficient-thinking

Model card Files Files and versions

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

Commit History

Clarify model comparison and report English/Python perplexity

c1703d2
verified

daavidhauser commited on 3 days ago

Release Swift 1.5 HyperQwen fast quantization with RTX 3090 evaluation

1613e65
verified

daavidhauser commited on 3 days ago