Nvidia Nemotron Nano 12B V2 VL BF16
NVIDIA develops the Nvidia Nemotron Nano 12B V 2 VL BF 16, a chat model exceling at multi-modal document intelligence, including visual Q&A, summarization, and multi-image reasoning. Its transformer architecture and large context window of 131,072 tokens enable handling complex inputs, such as multiple images and long text prompts.
Input
Output
Context
131K
Max Output
8K
Parameters
13.2B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens8,000 tokens
Parameters13.2B
Release DateOct 21, 2025
Training CutoffApr 23, 2025
Licenseother
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.3%
HLE
57.2%
GPQA
26.2%
SciCode
75.9%
MMLU Pro
75.0
Math
11.7
Coding
69.4%
LiveCodeBench
9.0
Intelligence
293
Speed (tok/s)
7.1
TTFA (s)
0.245
TTFT (s)
Resources & Links
Estimated GPU Requirements for Nvidia Nemotron Nano 12B V2 VL BF16
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.