1,847 9 hours ago

Dynamically quantized only 12GB MTP model with precision close to the base model picked from hugging face ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S-GGUF, highly efficient model

vision
ollama run logicbeat/qwen3.8-27B_GSQ_RCO

Details

9 hours ago

620290b584fb · 13GB

qwen35
·
27.3B
·
IQ3_S
clip
·
461M
·
BF16
{ "draft_num_predict": 3, "min_p": 0, "presence_penalty": 0, "repeat_penalty": 1,

Readme

No readme