nvidia/Gemma-4-31B-IT-NVFP4

Quantization vs google/gemma-4-31B-it. nvidia/Gemma-4-31B-IT-NVFP4 is a quantized version of the other (BF16/U8).

1 derivatives checked

• sartajbhuvaji/Gemma-4-31B-IT-NVFP4-FP8attn-text: LoRA-style

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

On the Hub · Downloads on Model Pulse