We've gone even farther: Nemotron 3 Super is 120B and pretrained on 25T tokens in NVFP4. Nemotron 3 Ultra is ~500B and also pretrained in NV…

We've gone even farther: Nemotron 3 Super is 120B and pretrained on 25T tokens in NVFP4. Nemotron 3 Ultra is ~500B and also pretrained in NVFP4. Accelerated computing means we rethink every aspect of the AI stack looking for new opportunities to improve efficiency. NVIDIA has done the impossible and nobody's talking about it. They trained a 12 BILLION parameter LLM in 4-bit precision on 10 trillion tokens. For years, the AI industry has been stuck. If you wanted to train a world-class AI, you had to use 16-bit or 8-bit precision. Going lowe…

Source: Jeremy Howard (X) | 2026-05-15