Llama-3.3-Nemotron-Super-49B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model's memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.
Added Aug 8, 2025
Context Window
128.0K
Max Output
16.4K
Input Price (Auto)
$0.15/1M
Output Price (Auto)
$0.15/1M
Cache Read (Auto)
$0.075/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
8.3
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
51.7%
Better than 27% of models compared
HLE
Humanity's Last Exam
3.8%
Better than 11% of models compared
IFBench
Instruction-following benchmark
39.5%
Better than 37% of models compared
AA-LCR
Long context reasoning evaluation
13.3%
Better than 22% of models compared
Coding
SciCode
Python programming for scientific computing
22.9%
Better than 24% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
0.0%
Better than 5% of models compared
LiveCodeBench
Contamination-free coding benchmark
28.0%
Better than 31% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
7.7%
Better than 12% of models compared
AIME
American Invitational Mathematics Examination
19.3%
Better than 46% of models compared
Math-500
Diverse mathematical problem solving benchmark
77.5%
Better than 42% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
69.8%
Better than 36% of models compared
Last updated Aug 16, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Nvidia Nemotron Super 49B with similar models from the same provider or model family.
Nvidia Nemotron 3 Super 120B
nvidia/nemotron-3-super-120b-a12bNvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.
Nvidia Nemotron 3 Super 120B Thinking
nvidia/nemotron-3-super-120b-a12b:thinkingNvidia Nemotron 3 Super 120B with reasoning content enabled. Returns separate thinking content when requested.
Nvidia Nemotron 70b
nvidia/Llama-3.1-Nemotron-70B-Instruct-HFNvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.
Nvidia Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightningNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant. Included in the NanoGPT subscription.
Nvidia Nemotron 3.5 Lightning Thinking
nvidia/nemotron-3.5-lightning:thinkingNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace. Included in the NanoGPT subscription.
Nvidia Nemotron 3 Ultra 550B
nvidia/nemotron-3-ultra-550b-a55bNvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.