Llama 3_3 Nemotron Super 49B V1
NVIDIA's Llama 3_3 Nemotron Super 49B V 1 is a large language model and chat model that excels at balancing model accuracy and efficiency, making it suitable for various tasks such as reasoning, human chat preferences, and tool calling. Its notable technical trait is the use of a novel Neural Architecture Search (NAS) approach, which reduces the model's memory footprint and enables larger workloads.
Input
Output
Context
131K
Max Output
4K
Parameters
49.9B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens4,096 tokens
Parameters49.9B
Release DateMar 16, 2025
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
6.5%
HLE
58.3%
AIME
64.3%
GPQA
28.2%
SciCode
95.9%
MATH 500
78.5%
MMLU Pro
54.7
Math
9.4
Coding
27.7%
LiveCodeBench
12.2
Intelligence
Resources & Links
Estimated GPU Requirements for Llama 3_3 Nemotron Super 49B V1
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 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.