Nemotron Nano 2 VL 12B
NVIDIA
- Released
- October 28, 2025
- Data date
- September 8, 2026
- Speed
- 71.8 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
- Input
- Text
- Output
- Text
Nemotron Nano 12B v2 VL adds the CRadioV2-H vision encoder to NVIDIA’s Nemotron language model. It was developed for image understanding, visual questions, and document analysis. The Amazon Bedrock service accepts image and text inputs and produces text.
The open VL model card specifies 12.6 billion parameters, up to four images, and a combined 128K-token input and output limit. Amazon Bedrock serves the checkpoint as nvidia.nemotron-nano-12b-v2 with a 128K-token context and a maximum 8K-token output.
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | Open weightsSource |
| Access | API, LocalSource |
| Notes | Open-weights vision model with 12B parameters and a 128K context window.Source |
| Amazon Bedrock model | NVIDIA Nemotron Nano 12B v2 VL BF16Source |
| Parameters | 12.6 billionSource |
| Context window | 128K tokensSource |
| Maximum output on Amazon Bedrock | 8K tokensSource |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Artificial Analysis Intelligence Index (Show measurement, test conditions, and source)
- Source value
- 5.82045753777258
- Score
- 5.82045753777258
- Metric
- points
- Unit
- points
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
AA-Omniscience Index (Show measurement, test conditions, and source)
- Source value
- -72.2333333333333
- Score
- -72.2333333333333
- Metric
- points
- Unit
- points
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
Output speed (Show measurement, test conditions, and source)
- Source value
- 71.7547329586375
- Score
- 71.7547329586375
- Metric
- tokens/s
- Unit
- tokens/s
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Latency reasoning time (Show measurement, test conditions, and source)
- Source value
- 0
- Score
- 0
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Latency input time (Show measurement, test conditions, and source)
- Source value
- 2.14564871900002
- Score
- 2.14564871900002
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Answer generation time (end-to-end timing breakdown) (Show measurement, test conditions, and source)
- Source value
- 6.968181461816901
- Score
- 6.968181461816901
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
End-to-end reasoning time component (Show measurement, test conditions, and source)
- Source value
- 0
- Score
- 0
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
End-to-end input time component (Show measurement, test conditions, and source)
- Source value
- 2.14564871900002
- Score
- 2.14564871900002
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. Non-reasoning
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Popularity
33 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Speed | Median across serving providers, Non-reasoning. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. |
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 8, 2026. |
| Output | Documented modalities. Retrieved September 8, 2026. |
| Research status | Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | active-parameters-billions Original wording No exact value located in the checked primary model card/API documentation. |
| Not found in the inspected sources | knowledge-cutoff Original wording No exact value located in the checked primary model card/API documentation. |
| Not found in the inspected sources | excluded-checkpoint-observations Original wording The separate text model's card does not establish specifications or scores for this VL checkpoint. |
| Additional source | Model metadata (retrieved October 2, 2026) · NVIDIA Nemotron Nano 12B v2 VL BF16 model card · Editorial description reviewed October 2, 2026 |
| Additional source | Context window data |
| Additional source | AWS Bedrock model card for NVIDIA Nemotron Nano 12B v2 VL BF16 (retrieved October 2, 2026) · Amazon Bedrock NVIDIA Nemotron Nano 12B v2 VL BF16 model card · 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 |