Nemotron 3.5 Super VL at a glance
NVIDIA released a 120B multimodal agent model plus Bolt models sized to run locally in 24GB and 4GB of memory.
Current standing
As of
- Rank
- #39of 43 models
Nemotron 3.5 Super VL (High) · 13.6 on the Artificial Analysis Intelligence Index v5.0.1 (opens in a new tab)
- Current leader
- Gemini 4 Carbon (Google) · 60
Computed from our daily snapshot; it changes as new models are measured. NVIDIA adds Nemotron 3.5 Super VL and Bolt open models for agents and local AI
What changed with Nemotron 3.5 Super VL
On October 15, 2026, NVIDIA released Nemotron 3.5 Super VL, an open 120B-parameter model for multimodal agent work that reads text, images, webpages, and PDFs. It also introduced Bolt 74B-A9B, which uses native 2-bit quantization to fit in 24GB, and a 4GB Bolt E4B edge model due October 23.
NVIDIA says the models ship with open weights, datasets, and training recipes. Super VL is on Hugging Face, OpenRouter, ModelScope, and NVIDIA NIM; Bolt 74B-A9B supports llama.cpp, Ollama, LM Studio, and vLLM. Speed and ranking claims are NVIDIA's own.
Where to compare Nemotron 3.5 Super VL
Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.
Leaderboards
General leaderboards
Why Nemotron 3.5 Super VL matters for businesses
Models that run well on a single workstation let small businesses keep sensitive documents on their own hardware while still using agent-style workflows.
Nemotron 3.5 Super VL updates since publication
Dated changes since publication. The original article text above is kept as written on its date.
Availability (Updated)
Nemotron 3.5 Bolt E4B 4GB is now available, with support for llama.cpp, vLLM, Ollama, Unsloth and LM Studio.
blogs.nvidia.com (opens in a new tab)
Sources for this story
- Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models (opens in a new tab)Official
NVIDIA Blog · blogs.nvidia.com
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #llm
- #nvidia
- #nemotron
- #open-weights
- #local-ai
