Nvidia Nemotron Nano 9B V2 FP8
NVIDIA develops the Nvidia Nemotron Nano 9B V 2 FP 8, a large language model designed for unified reasoning and non-reasoning tasks, with capabilities in code generation and reasoning. It is genuinely best at generating high-quality final solutions to queries and tasks when allowed to produce intermediate reasoning traces.
Input
Output
Context
131K
Max Output
2K
Parameters
8.9B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens2,048 tokens
Parameters8.9B
Release DateSep 22, 2025
Training CutoffSep 1, 2024
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.6%
HLE
57.0%
GPQA
22.0%
SciCode
74.2%
MMLU Pro
69.7
Math
8.3
Coding
72.4%
LiveCodeBench
8.8
Intelligence
58.9
Speed (tok/s)
51.6
TTFA (s)
17.6
TTFT (s)
Resources & Links
Estimated GPU Requirements for Nvidia Nemotron Nano 9B V2 FP8
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.