nvidia/Gemma-4-26B-A4B-NVFP4

Quantization vs google/gemma-4-26B-A4B-it. nvidia/Gemma-4-26B-A4B-NVFP4 is a quantized version of the other (U8/BF16).

2 derivatives checked

• catlilface/Gemma-4-26B-A4B-NVFP4-GGUF: Same weights, converted
• williamliao/Gemma-4-26B-A4B-NVFP4-GGUF: Same weights, converted

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

On the Hub · Downloads on Model Pulse