Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8

Quantization vs Qwen/Qwen2-1.5B-Instruct. Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8 is a quantized version of the other (F32/I32).

On the Hub · Downloads on Model Pulse