DigitalOcean(@digitalocean):Glean post-trained NVIDIA Nemotron 3 Nano for enterprise search and got 50% lower latency and 25% fewer tokens, "without any sort of loss in accuracy." That's the example @NVIDIA's @Shashank__Verma gave on the Serve track at Open Intelligence Summit, behind a bigger point: "a model can be open source and frontier at the same time." Serve track, Open Intelligence Summit.

DigitalOcean

@digitalocean

The AI-Native Cloud. ☁️ Status: @DOstatus Support:

加入 January 2012

272 正在關注 226.6K 粉絲

DigitalOcean@digitalocean

2026.10.15 20:37

Glean post-trained NVIDIA Nemotron 3 Nano for enterprise search and got 50% lower latency and 25% fewer tokens, "without any sort of loss in accuracy." That's the example @NVIDIA's @Shashank__Verma gave on the Serve track at Open Intelligence Summit, behind a bigger point: "a model can be open source and frontier at the same time." Serve track, Open Intelligence Summit.