huawei-csl
/

Qwen3-1.7B-4bit-SINQ

Text Generation

efficient-inference

8-bit precision

Model card Files Files and versions

Qwen3-1.7B-4bit-SINQ / chat_template.jinja

Commit History

Initial upload: sharded safetensors + tokenizer

a76f3cc
verified

chiaraboretti commited on Oct 17