Nemotron Nano 9B v2
Unavailable in this round
Language model
Nemotron Nano 9B v2
NVIDIA
- Released
- August 18, 2025
- Data date
- September 26, 2026
- Input
- Text
- Output
- Text
Nemotron Nano 9B v2 combines Mamba2 and MLP layers with only four attention layers. Reasoning can be enabled, disabled, or constrained with a thinking budget.
The model card lists German, English, French, and Japanese among the supported languages. NVIDIA publishes its own comparisons with Qwen3-8B using reasoning mode, except for the RULER long-context test. RULER runs without an additional reasoning trace.
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Popularity
14.7 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Input | Documented modalities. Retrieved September 26, 2026. |
| Output | Documented modalities. Retrieved September 26, 2026. |
| Additional source | NVIDIA Nemotron Nano 9B v2 model card · Editorial description reviewed October 2, 2026 |
| Additional source | NVIDIA Nemotron Nano 2 technical report · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |