We used a *lot* of Modal GPU hours this month testing Nemotron 3 Super and…

March 11, 2026

We used a *lot* of Modal GPU hours this month testing Nemotron 3 Super and tinkering with inference tooling. (Yay open source!) Thanks to the @modal team for the fantastic developer tooling and always being wonderful to work with. Highly recommended. https://t.co/3Klnlt8jpE

Modal@modal

Deploy Nemotron 3 Super, the latest open model from @nvidia, today on Modal.

Its hybrid architecture delivers >50% faster token generation compared to the best open models today.