Nemotron-3 Nano-30B is a new-generation LLM from NVIDIA. The model's key feature is its innovative architecture, which integrates Mamba2 layers, Transformer layers, and Mixture-of-Experts (MoE) technology into a unified compute cluster. This structure allows the model to efficiently process massive datasets while maintaining logical coherence and high throughput. The model has a total parameter count of 32 billion, but thanks to MoE routing, only an active subset of approximately 3.5 billion parameters is engaged for generating each individual token. This provides a unique balance: the model possesses the "knowledge" and capacity of a 30B-scale network but consumes computational resources on par with compact models optimized for fast inference. The model was trained on a dataset of about 25 trillion tokens, encompassing 43 programming languages and more than 19 natural languages.
Compared to Nemotron v2, the new version offers an MoE architecture instead of a dense one, delivering 4 times greater throughput. Another key capability of Nemotron-3 Nano is support for a context window of up to 1 million tokens. This expansion ideally showcases the capabilities of Mamba2 layers, which process long sequences with minimal memory overhead. A crucial stage in the model's creation was Multi-environment Reinforcement Learning using the NeMo Gym library. The model was trained not just to answer questions, but to perform action sequences: calling tools, writing functional code, and constructing multi-step plans. This makes its behavior more predictable and reliable in complex scenarios where step-by-step result verification is required.
On the AIME25 benchmark (American Invitational Mathematics Examination), which tests mathematical and quantitative reasoning, Nemotron 3 Nano achieves 99.2% accuracy with tool use, surpassing GPT-OSS-20B at 98.7%. On LiveCodeBench (v6 2025-08–2025–05), the model scores 68.2%, outperforming Qwen3-30B (66.0%) and GPT-OSS-20B (61.0%). On other benchmarks, the model either leads or is on par with its counterparts.
Given its architectural advantages and NVIDIA's recommendations, the model is ideally suited for the following tasks: Agentic Systems and Orchestration, Long-Context RAG, Local/On-Prem and Edge Computing, Code Generation, and Data Structuring.
| Model Name | Context | Type | GPU | TPS | Tooling | Status | Link |
|---|---|---|---|---|---|---|---|
| stelterlab/NVIDIA-Nemotron-3-Nano-30B-A3B-AWQ | 262,144.0 | Public | — | 463.00 | yes | AVAILABLE | chat |
curl https://chat.immers.cloud/v1/endpoints/nemotron3-nano-30b-a3b/generate/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer USER_API_KEY" \
-d '{"model": "NVIDIA-Nemotron-3-Nano-30B-A3B", "messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"}
], "temperature": 0, "max_tokens": 150}'
$response = Invoke-WebRequest https://chat.immers.cloud/v1/endpoints/nemotron3-nano-30b-a3b/generate/chat/completions `
-Method POST `
-Headers @{
"Authorization" = "Bearer USER_API_KEY"
"Content-Type" = "application/json"
} `
-Body (@{
model = "NVIDIA-Nemotron-3-Nano-30B-A3B"
messages = @(
@{ role = "system"; content = "You are a helpful assistant." },
@{ role = "user"; content = "Say this is a test" }
)
} | ConvertTo-Json)
($response.Content | ConvertFrom-Json).choices[0].message.content
#!pip install OpenAI --upgrade
from openai import OpenAI
client = OpenAI(
api_key="USER_API_KEY",
base_url="https://chat.immers.cloud/v1/endpoints/nemotron3-nano-30b-a3b/generate/",
)
chat_response = client.chat.completions.create(
model="NVIDIA-Nemotron-3-Nano-30B-A3B",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"},
]
)
print(chat_response.choices[0].message.content)
Rent your own physically dedicated instance with hourly or long-term monthly billing.
We recommend deploying private instances in the following scenarios:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 |
1 | $0.53 | 1.024 | Launch | ||
262,144.0 tensor |
2 | $0.54 | 3.347 | Launch | ||
262,144.0 tensor |
2 | $0.57 | 3.395 | Launch | ||
262,144.0 |
1 | $0.83 | 1.655 | Launch | ||
262,144.0 pipeline |
3 | $0.84 | 1.893 | Launch | ||
262,144.0 |
1 | $1.02 | 1.632 | Launch | ||
262,144.0 tensor |
4 | $1.12 | 3.961 | Launch | ||
262,144.0 tensor |
2 | $1.23 | 12.800 | Launch | ||
262,144.0 |
1 | $1.59 | 6.292 | Launch | ||
262,144.0 tensor |
4 | $1.82 | 2.830 | Launch | ||
262,144.0 |
1 | $2.37 | 181.920 | 34.804 | Launch | |
262,144.0 |
1 | $3.83 | 34.762 | Launch | ||
262,144.0 |
1 | $4.11 | 43.042 | Launch | ||
262,144.0 tensor |
2 | $4.61 | 80.358 | Launch | ||
262,144.0 |
1 | $4.74 | 70.845 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 152.440 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
2 | $0.93 | 2.847 | Launch | ||
262,144.0 tensor |
4 | $0.96 | 3.746 | Launch | ||
262,144.0 tensor |
2 | $1.23 | 2.847 | Launch | ||
262,144.0 tensor |
4 | $1.26 | 3.794 | Launch | ||
262,144.0 tensor |
2 | $1.56 | 4.109 | Launch | ||
262,144.0 tensor |
2 | $1.92 | 4.061 | Launch | ||
262,144.0 |
1 | $2.37 | 24.851 | Launch | ||
262,144.0 tensor |
2 | $2.93 | 13.382 | Launch | ||
262,144.0 |
1 | $3.83 | 134.650 | 24.809 | Launch | |
262,144.0 |
1 | $4.11 | 33.089 | Launch | ||
262,144.0 tensor |
2 | $4.61 | 70.405 | Launch | ||
262,144.0 |
1 | $4.74 | 60.892 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 142.487 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
4 | $1.76 | 3.118 | Launch | ||
262,144.0 |
1 | $2.51 | 4.691 | Launch | ||
262,144.0 tensor |
4 | $2.97 | 4.380 | Launch | ||
262,144.0 tensor |
4 | $3.68 | 4.333 | Launch | ||
262,144.0 |
1 | $3.96 | 4.649 | Launch | ||
262,144.0 |
1 | $4.12 | 12.929 | Launch | ||
262,144.0 pipeline |
3 | $4.35 | 5.796 | Launch | ||
262,144.0 |
1 | $4.74 | 40.732 | Launch | ||
262,144.0 tensor |
2 | $4.94 | 50.245 | Launch | ||
262,144.0 tensor |
4 | $5.76 | 13.654 | Launch | ||
262,144.0 tensor |
2 | $9.41 | 122.327 | Launch | ||
Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.