nvidia/Qwen3-VL-235B-A22B-Instruct-NVFP4

Quantization vs Qwen/Qwen3-VL-235B-A22B-Instruct. nvidia/Qwen3-VL-235B-A22B-Instruct-NVFP4 is a quantized version of the other (U8/F8_E4M3).

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

On the Hub · Downloads on Model Pulse