INC4AI/Qwen2.5-VL-7B-Instruct-int4-mixed-AutoRound

Quantization vs Qwen/Qwen2.5-VL-7B-Instruct. INC4AI/Qwen2.5-VL-7B-Instruct-int4-mixed-AutoRound is a quantized version of the other (I32/BF16).

On the Hub · Downloads on Model Pulse