nvidia/Qwen2.5-VL-7B-Instruct-NVFP4

Quantization vs Qwen/Qwen2.5-VL-7B-Instruct. nvidia/Qwen2.5-VL-7B-Instruct-NVFP4 is a quantized version of the other (BF16/U8).

On the Hub · Downloads on Model Pulse