nvidia/Qwen3-14B-NVFP4
Quantization vs Qwen/Qwen3-14B. nvidia/Qwen3-14B-NVFP4 is a quantized version of the other (U8/BF16).
1 other repos hold byte-for-byte identical weight files.
Quantization vs Qwen/Qwen3-14B. nvidia/Qwen3-14B-NVFP4 is a quantized version of the other (U8/BF16).
1 other repos hold byte-for-byte identical weight files.