Tech
NVIDIA brings open Nemotron agents from data centers to local devices
NVIDIA released three open Nemotron models spanning enterprise servers, local computers, and edge devices.
What happened
NVIDIA released Nemotron 3.5 Super VL, an open 120-billion-parameter model for multimodal agentic tasks, alongside two smaller Bolt models for local deployment. Super VL and Bolt 74B-A9B 24GB are available now; Bolt E4B 4GB is scheduled for October 23. The models support customization, private deployment, and workloads across NVIDIA’s hardware stack.
Why it matters
Organizations can run and adapt agents on their own infrastructure, keeping data private while matching model size and capability to enterprise, desktop, or edge workloads.
Source: NVIDIA Blog