Skip to content
Read the original: NVIDIA BlogOfficial· Pick75/100AI score75/100

NVIDIA releases open Nemotron 3.5 Super VL and Bolt edge models for agents

Original titleOpen From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models

AISummary

NVIDIA releases Nemotron 3.5 Super VL, an open 120-billion-parameter multimodal model that it says is 5x faster than the next best open model in its class on agentic workloads.

The company also releases Nemotron 3.5 Bolt 74B-A9B 24GB, which runs locally in 24GB of memory with native 2-bit quantization, and Bolt E4B 4GB, with E4B coming Oct. 23. Super VL and Bolt 74B-A9B are available now.

Read the original blogs.nvidia.com

Source: NVIDIA Blog · blogs.nvidia.comPublished · added here