Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8

Quantization vs Qwen/Qwen2.5-7B-Instruct. Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8 is a quantized version of the other (I32/F16).

On the Hub · Downloads on Model Pulse