RedHatAI/Qwen3-VL-32B-Instruct-FP8-dynamic

Quantization vs Qwen/Qwen3-VL-32B-Instruct. RedHatAI/Qwen3-VL-32B-Instruct-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).

On the Hub · Downloads on Model Pulse