NVIDIA Blog

NVIDIA expands Nemotron with Super VL and two Bolt edge models

NVIDIA says its new open model, Nemotron 3.5 Super VL, has 120 billion parameters and leads on accuracy and task completion speed for specialized agents running continuously. Two edge models join it: Nemotron 3.5 Bolt 74B-A9B 24GB, focused on balancing per-GB intelligence and speed for local agentic workloads, and Nemotron 3.5 Bolt E4B 4GB.

Source published: Brief prepared:
NVIDIA expands Nemotron with Super VL and two Bolt edge models
Image source · NVIDIA Blog

What to know

  • 01

    Nemotron 3.5 Super VL is an open model with 120 billion parameters, aimed at specialized, always-on agents.

  • 02

    The edge additions are Nemotron 3.5 Bolt 74B-A9B 24GB and Nemotron 3.5 Bolt E4B 4GB; the former is optimized for local agentic workloads.

Why it matters

The expansion is relevant to model choices for specialized, always-on agents and local agentic workloads.

Original sourceRead the source · NVIDIA Blogblogs.nvidia.com

AI-assisted brief. Read the source for full details. Editorial & sourcing policy