Qwen/Qwen2-VL-7B-Instruct-AWQ

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

3 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse