nvidia/Qwen3-235B-A22B-Thinking-2507-NVFP4

Quantization vs Qwen/Qwen3-235B-A22B-Thinking-2507. nvidia/Qwen3-235B-A22B-Thinking-2507-NVFP4 is a quantized version of the other (U8/F8_E4M3).

On the Hub · Downloads on Model Pulse