squishai
/

Qwen3-0.6B-bf16-squished

4-bit precision

Model card Files Files and versions

Qwen3-0.6B-bf16-squished / model.safetensors.index.json

Commit History

Add Qwen3-0.6B INT4 squished weights

76347e3
verified

wscholl commited on 4 days ago