Nemotron 3.5 Super VL leads US open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → models at 26 on the Intelligence Index with about 60% fewer output tokens than its predecessor and near-lossless NVFP4, which matters for self-hosted AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → cost.
Key takeaways · AI-distilled
Artificial Analysis reports that Nemotron 3.5 Super VL uses about 60% fewer output tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per Intelligence Index task than Nemotron 3 Super, while scoring higher.
Nemotron 3.5 Super VL reached 630 output tokens per second on a pre-release DeepInfra endpoint using NVFP4 weights and 100,000-token prompts. The result applies to that serving setup.
Nemotron 3.5 Bolt uses fewer parameters than Nemotron 3 Ultra but has mixed task results. It leads on AutomationBench-AA and AA-Briefcase while trailing on long-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → reasoning and Humanity's Last Exam.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
