Models · Model provider

NVIDIA

NVIDIA publishes Nemotron text, vision, speech and retrieval models and offers GPU inference through NIM.

+ Follow

Builder facts

  • Nemotron distribution. Nemotron 3.5 Super VL and Lightning are available as downloadable checkpoints, NVIDIA NIM endpoints and separately routed OpenRouter endpoints. Source ↗
  • Local vision model. Nemotron 3.5 Bolt 74B-A9B 24GB uses native 2-bit quantization to fit 24 GB of memory and ships under the OpenMDW 1.1 license. Source ↗
  • NIM access. NVIDIA Developer Program membership includes hosted endpoints for prototyping. NVIDIA AI Enterprise and dedicated partner endpoints offer separate production deployment options. Source ↗

Sources checked

Publisher update ·

NVIDIA releases the Nemotron-Labs Sigma NFE16 checkpoint ↗

The downloadable 8-billion-parameter NFE16 research checkpoint produces 32-token blocks with 16 denoising evaluations and a final readout.

Change timeline

0 stories

No verified releases in this timeline yet.