Vishva007/Qwen3-VL-8B-Instruct-W4A16-AutoRound

Quantization vs Qwen/Qwen3-VL-8B-Instruct. Vishva007/Qwen3-VL-8B-Instruct-W4A16-AutoRound is a quantized version of the other (F16/I32).

On the Hub · Downloads on Model Pulse