nvidia · Open weights
Nvidia Nemotron Super 49B
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.
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.15
- Output
- $0.15
Reference prices as published by the model provider. API example
Specifications
- Context window
- 128K
- Max output
- 16.4K
Side by side
Nvidia Nemotron Super 49B compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Nvidia Nemotron Super 49BnvidiaThis model | Qwen 3 32bQwenRemove | |
|---|---|---|
| Provider | nvidia | Qwen |
| Discovery tier | Open weights | Open weights |
| Added | Aug 8, 2025 | Jan 1, 2024 |
| Limits | ||
| Context window | 128KBest | 41K |
| Max output | 16.38K | 32.77KBest |
| Average output | — | 646 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.15 | $0.08Best |
| Output | $0.15Best | $0.24 |
| Performance | ||
| Throughput | — | 29.1 tok/s |
| Time to first token | — | 3.0 s |
| Request success (24h) | — | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 7.3 | 7.3 |
| Math Index | 7.7 | 19.7Best |
| Capabilities | ||
| Tools | No | Yes |
| PDF input | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Nvidia Nemotron Super 49B
- Qwen 3 32b
Intelligence Index
- Nvidia Nemotron Super 49B7.3
- Qwen 3 32b7.3
Nvidia Nemotron Super 49B: Better than 10% of 326 scored models
Indexes
Math Index
Composite of the math evaluations
- Nvidia Nemotron Super 49B: 7.7
- Qwen 3 32b: 19.7Top
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- Nvidia Nemotron Super 49B: 12.0%Top
- Qwen 3 32b: 0.0%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Nvidia Nemotron Super 49B: 3.8%
- Qwen 3 32b: 4.1%Top
GPQA Diamond
Graduate-level science questions
- Nvidia Nemotron Super 49B: 51.7%
- Qwen 3 32b: 53.5%Top
MMLU-Pro
Multi-subject knowledge and reasoning
- Nvidia Nemotron Super 49B: 69.8%
- Qwen 3 32b: 72.7%Top
IFBench
Following precise output instructions
- Nvidia Nemotron Super 49B: 39.5%Top
- Qwen 3 32b: 31.5%
Coding
LiveCodeBench
Recent competitive programming problems
- Nvidia Nemotron Super 49B: 28.0%
- Qwen 3 32b: 28.8%Top
Math
AIME 2025
Competition mathematics, 2025 problems
- Nvidia Nemotron Super 49B: 7.7%
- Qwen 3 32b: 19.7%Top
AIME
Competition mathematics
- Nvidia Nemotron Super 49B: 19.3%
- Qwen 3 32b: 30.3%Top
MATH-500
Competition math problems
- Nvidia Nemotron Super 49B: 77.5%
- Qwen 3 32b: 86.9%Top
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Nvidia Nemotron Super 49B: 0.0%
- Qwen 3 32b: —
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Nvidia Nemotron Super 49B: 12.0%Top
- Qwen 3 32b: 0.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/Llama-3.3-Nemotron-Super-49B-v1",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="nvidia/Llama-3.3-Nemotron-Super-49B-v1",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)nvidia
Related models
Other nvidia models, starting with the same family.