nvidia/Qwen3-8B-NVFP4
Quantization vs Qwen/Qwen3-8B. nvidia/Qwen3-8B-NVFP4 is a quantized version of the other (U8/BF16).
3 other repos hold byte-for-byte identical weight files.
Quantization vs Qwen/Qwen3-8B. nvidia/Qwen3-8B-NVFP4 is a quantized version of the other (U8/BF16).
3 other repos hold byte-for-byte identical weight files.