Tools & PluginsThursday, October 15, 2026
Hermes + NVIDIA Nemotron 3.5 Super VL
Nous Research highlighted Hermes Agent as the best place to run the new NVIDIA Nemotron 3.5 Super VL (and Bolt) models. NVIDIA benchmarked Super VL on Hermes Bench at 63.44; compared with similar local models it offers up to 5× token throughput. Community demos quickly appeared showing vision + tool use for practical tasks.
Why it matters
Gives local/agentic users a strong open model option with real Hermes-specific performance numbers. Reinforces Hermes as a preferred runtime for new open models.