meituan
/

DeepSeek-R1-Channel-INT8

Text Generation

8-bit precision

Model card Files Files and versions Community

Resources

View closed (3)

can this model run with `ollama` with `pure cpu` model?

#7 opened 1 day ago by

Add `quantization_config` in config.json?

#4 opened 6 days ago by

运行channel INT8后sglang报错OOM

#3 opened 8 days ago by

Difference with Block-wise Int8?

#1 opened 13 days ago by