hfl/Qwen2.5-VL-3B-Instruct-GPTQ-Int4

Quantization vs Qwen/Qwen2.5-VL-3B-Instruct. hfl/Qwen2.5-VL-3B-Instruct-GPTQ-Int4 is a quantized version of the other (BF16/I32).

On the Hub · Downloads on Model Pulse