nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

Quantization vs nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 is a quantized version of the other (F8_E4M3/BF16).

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

On the Hub · Downloads on Model Pulse