techwithsergiu
/

Qwen3.5-text-4B-bnb-4bit

Text Generation

4-bit precision

Model card Files Files and versions

Qwen3.5-text-4B-bnb-4bit / config.json

Commit History

Fixed quantization_config.llm_int8_skip_modules, to avoid re-quantizes embed_tokens layers on load

159a450
verified

techwithsergiu commited on Mar 11

Upload a quantized Text-Only BNB 4-bit model

b21ca6a
verified

techwithsergiu commited on Mar 6