Text and chat · NVIDIA
Nemotron
NVIDIA's open models for agent work: Super VL reads images and video, Ultra handles long tool-driven tasks, Nano is small and cheap. Private mode.
Private Low costWhat sets it apart
Nemotron 3 is NVIDIA’s open family built on a hybrid Mamba and Transformer mixture-of-experts design, tuned with reinforcement learning on multi-step tool tasks. Ultra scales it to 550B parameters, Super VL adds image and video reading with 12B active, and Nano keeps 3B active for speed and price.
- Hybrid Mamba, Transformer and MoE design
- Trained with RL on tool and code tasks
- Ultra: 550B total, 55B active, open weights
Strengths and limits
Where it shines
- Ultra is built for long agent runs with many tool calls
- Private mode, moderate price
- Super VL reads images and video, has open weights and scores highest of the family on the index
Think twice when
- Ultra and Nano read text only; images and video come with Super VL
- Ultra: 550B parameters, 55B active, 256K context here. Super VL: 120B, 12B active, 262K here
- Open weights
Use cases
Long multi-step agent task
Audit this repository: list the five modules with the most duplicated logic, open each one, and propose a refactoring order with risks.
Ultra is trained for long tool-driven runs.
Cheap classification at scale
Classify each of these 500 support messages as billing, bug, feature request or other, and return one label per line.
Nano is small, fast and among the cheapest models in the catalog.
Reading a screenshot or a scanned page
Here is a screenshot of an error dialog and a photo of an invoice: tell me what the error means and list the invoice lines with their totals.
Super VL reads images, documents and GUIs, which Ultra and Nano do not.
Against its rivals
- GPT OSSgpt-oss is the other large open reasoning model, with a lower price at similar size.#79 of 90 on Artificial Analysis Intelligence Index (12 points)
- Qwen open modelsQwen open models also read images; in Nemotron only Super VL does, and Qwen has more sizes to choose from.#23 of 90 on Artificial Analysis Intelligence Index (40 points)
- GLMGLM scores higher on agent work and costs more.#13 of 90 on Artificial Analysis Intelligence Index (45 points)
Version history
Each version, dated, with what it changed over the one before.
Hollow points are earlier versions no longer offered in Sub Rosa.
See the numbers
| Version | Released | points |
|---|---|---|
| Nemotron 3 Nano 30B A3B | 2025-12-15 | 7 |
| Nemotron 3 Ultra 550B A55B | 2026-06-04 | 23 |
| Nemotron 3.5 Super VL 120B A12B | 2026-10-15 | 26 |
- Nemotron 3 Nano 30B A3B
- Introduced the family: hybrid Mamba, Transformer and MoE with about 3.5B active parameters
- Up to 1M token context and a switchable reasoning mode
- Nemotron 3 Ultra 550B A55B
- 550B total and 55B active parameters, the largest of the family
- Intelligence Index 23 versus 7 for Nano, with reasoning and 262K context
- Nemotron 3.5 Super VL 120B A12BLatest
- Vision-language model with 120B total and 12B active parameters, reading text, images and video, with an optional reasoning mode.
- Scores 26 on the Artificial Analysis index, against 23 for Ultra; open weights under OpenMDW-1.1.
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Intelligence Index: #52 of 90 models measured in the catalog. One score averaging about ten independent tests of reasoning, knowledge, math, coding and agent work, all run the same way for every model. Higher is better. Each model is listed at its highest reasoning effort. Two or three points apart is a close call; ten points is a different class of model.
See the numbers
| Model | points |
|---|---|
| 1. Claude Opus 5.5 | 58 |
| 2. Claude Sonnet 5.5 | 56 |
| 3. Claude Fable 5.1 | 53 |
| 4. GPT-6 Astra | 53 |
| 5. Gemini 4 Argon | 53 |
| 6. GPT-6.1 Sol | 52 |
| 7. Muse Wonder | 52 |
| 8. Claude Opus 5 | 51 |
| 9. Claude Fable 5 | 50 |
| 10. GPT-6 Sol | 48 |
| 52. NVIDIA Nemotron 3.5 Super VL 120B | 26 |
| 63. NVIDIA Nemotron 3 Ultra | 23 |
| 89. NVIDIA Nemotron 3 Nano 30B | 7 |
Announced by the maker
Measured by the maker with its own settings: useful, but not directly comparable with the independent scores above.
| Benchmark | Model | Score | Source |
|---|---|---|---|
| swe-bench-verified | NVIDIA Nemotron 3.5 Super VL 120B | 71.1 | huggingface.co |
| gpqa-diamond | NVIDIA Nemotron 3.5 Super VL 120B | 89.52 | huggingface.co |
All 3 models in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
NVIDIA Nemotron 3 Ultranvidia-nemotron-3-ultra-550b-a55b | Text | Private | $1.405 per million tokens written$0.000984 a page written |
NVIDIA Nemotron 3 Nano 30Bnvidia-nemotron-3-nano-30b-a3b | Text | Private | $0.135 per million tokens written$0.0000944 a page written |
NVIDIA Nemotron 3.5 Super VL 120Bnvidia-nemotron-3-5-super-vl-120b-a12b | Text | Private | $0.562 per million tokens written$0.000393 a page written |
Specifications
| Specification | Nemotron 3.5 Super VL | Nemotron 3 Ultra | Nemotron 3 Nano |
|---|---|---|---|
| Released | October 15, 2026 | June 4, 2026 | December 15, 2025 |
| Parameters | 120B total, 12B active | 550B total, 55B active | 30B total, 3.5B active |
| Weights | Open, OpenMDW-1.1 | Open, OpenMDW | Open, NVIDIA Nemotron Open Model License |
| Accepts | text, images, video | text | text |
| Produces | text | text | text |
| Context | 262K tokens | 256K tokens | 128K tokens |
| Longest answer | · | 33K tokens | 16K tokens |
| Languages | English plus 6 languages emphasized in post-training | · | 6 languages |
| Abilities | Reads images, Uses Sub Rosa’s tools, Thinks before answering, Tuned for code | Uses Sub Rosa’s tools, Thinks before answering | Uses Sub Rosa’s tools |
| Price | $0.562 per million tokens written | $1.405 per million tokens written | $0.135 per million tokens written |
| Privacy | Private | Private | Private |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.
Show the 10 sources
- huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- developer.nvidia.com/blog/inside-nvidia-nemotron-3-techniques-tools-and-data-that-make-it-efficient-and-accurate
- artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b
- artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b
- api.venice.ai/api/v1/models
- pasqualepillitteri.it/en/news/3924/nemotron-3-ultra-nvidia-open-model
- nvidia.com/en-us/ai-data-science/foundation-models/nemotron
- huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
- artificialanalysis.ai/models/nemotron-3-5-super-vl