Nvidia Opens the Nemotron Floodgates: 120B Super VL Plus Two Edge Models

Nvidia expanded its Nemotron family with Nemotron 3.5 Super VL, a 120-billion-parameter open model built for always-on agents that need fast task completion and high accuracy. Alongside it came two edge variants: Nemotron 3.5 Bolt 74B-A9B in a 24GB footprint tuned for local agentic workloads, and the tiny Bolt E4B at just 4GB. The release spans data center to desktop, giving developers a single open model lineage to scale across deployment targets. For teams that have been renting frontier intelligence per token, this is a direct challenge to that cost structure.

Nemotron 3.5 Super VL: 120B open parameters optimized for specialized always-on agents

Nemotron 3.5 Bolt 74B-A9B fits in 24GB and targets local agentic workloads

Nemotron 3.5 Bolt E4B squeezes into 4GB for the smallest edge deployments

The family is designed to run from data center down to desktop with consistent tooling

Source: https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/