Local ModelsMedium importance
NVIDIA launches Nemotron for Science, with an open model that runs locally on a 128 GB DGX Spark and an open chemistry dataset
NVIDIA introduced on Monday (11/16) Nemotron for Science, a package that brings together the open Nemotron 3.5 Super VL model, scientific evaluations, a new open chemistry dataset and post-training recipes for researchers to build scientific agents, for example for chemistry experiments and protein design. LitmusBench v0.2 serves both to evaluate and to post-train chemistry reasoning. The model and LitmusBench are on Hugging Face, and Nemotron 3.5 Super VL was optimized to run locally on a 128 GB DGX Spark. According to NVIDIA, the US Department of Energy's Argonne National Laboratory is among the institutions already using Nemotron to build agents.
Published in edition no. 34 of Noticiário do Joãozinho ·
Translated by Joãozinho AI from the original Brazilian Portuguese edition. Facts, numbers and sources are the same as in the original; quotes, video titles and source names stay in their original language. Read the original in Portuguese
Original source
https://nvidianews.nvidia.com/news/nvidia-introduces-nemotron-for-science-to-accelerate-discoveries-with-agents