NVIDIA says hosted RL raised Nemotron 3 Nano from 22% to 91% for under $5

NVIDIAAI · x · 2026-07-24

NVIDIA says a hosted RL run took Nemotron 3 Nano from 22% to 91% accuracy on a math task for under $5.

Using Prime Intellect Lab, the workflow runs on hosted infrastructure: check a baseline, train until the reward improves, then retest to verify the model really learned. The result is a downloadable LoRA adapter.

NVIDIA also says the same setup can be scaled to Nemotron 3 Super and Ultra by changing one line.

Related event: NVIDIA Boosts Nemotron Model Accuracy to 91% for Under $5(3 posts)→

Original post →

More from Infra

Infra channel →