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 | 263K | Public | 4090 | 477.0 | yes | AVAILABLE | chat |
curl https://chat.immers.cloud/v1/endpoints/generate/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer USER_API_KEY" \
--data-binary @- <<"EOF"
{"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
}
EOF
$response = Invoke-WebRequest https://chat.immers.cloud/v1/endpoints/generate/chat/completions `
-Method POST `
-Headers @{
"Authorization" = "Bearer USER_API_KEY"
"Content-Type" = "application/json; charset=utf-8"
} `
-Body ([System.Text.Encoding]::UTF8.GetBytes((@{
model = "NVIDIA-Nemotron-3-Nano-30B-A3B"
messages = @(
@{ role = "system"; content = "You are a helpful assistant." },
@{ role = "user"; content = "Say this is a test" })
} | ConvertTo-Json -Depth 10)))
([System.Text.Encoding]::UTF8.GetString($response.RawContentStream.ToArray()) | 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/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)
# linux
export ANTHROPIC_BASE_URL=https://chat.immers.cloud/v1/endpoints/generate/
export ANTHROPIC_API_KEY=USER_API_KEY
export ANTHROPIC_MODEL=NVIDIA-Nemotron-3-Nano-30B-A3B
# windows (ps)
[Environment]::SetEnvironmentVariable("ANTHROPIC_BASE_URL", "https://chat.immers.cloud/v1/endpoints/generate/", "User")
[Environment]::SetEnvironmentVariable("ANTHROPIC_AUTH_TOKEN", "USER_API_KEY", "User")
[Environment]::SetEnvironmentVariable("ANTHROPIC_MODEL", "NVIDIA-Nemotron-3-Nano-30B-A3B", "User")
# linux
export OPENAI_BASE_URL=https://chat.immers.cloud/v1/endpoints/generate/
export OPENAI_API_KEY=USER_API_KEY
export OPENAI_MODEL=NVIDIA-Nemotron-3-Nano-30B-A3B
# windows (ps)
[Environment]::SetEnvironmentVariable("OPENAI_BASE_URL", "https://chat.immers.cloud/v1/endpoints/generate/", "User")
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "USER_API_KEY", "User")
[Environment]::SetEnvironmentVariable("OPENAI_MODEL", "NVIDIA-Nemotron-3-Nano-30B-A3B", "User")
An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.
A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.
We recommend creating private endpoints when you need to:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
2 | $0.57 | 2.984 | Launch | ||
262,144.0 tensor |
2 | $0.93 | 12.489 | Launch | ||
262,144.0 |
1 | $1.02 | 477.00 | 2.250 | Launch | |
262,144.0 tensor |
2 | $1.56 | 13.764 | Launch | ||
262,144.0 |
1 | $1.59 | 6.005 | Launch | ||
262,144.0 |
1 | $2.37 | 223.80 | 34.269 | Launch | |
262,144.0 |
1 | $3.83 | 209.21 | 34.773 | Launch | |
262,144.0 |
1 | $4.11 | 244.39 | 42.435 | Launch | |
262,144.0 tensor |
2 | $4.61 | 80.764 | Launch | ||
262,144.0 |
1 | $4.74 | 69.997 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 153.612 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
2 | $2.93 | 20.070 | Launch | ||
262,144.0 |
1 | $3.83 | 134.65 | 45.531 | Launch | |
262,144.0 |
1 | $4.11 | 61.465 | Launch | ||
262,144.0 |
1 | $4.74 | 114.974 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 276.071 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
4 | $1.62 | 3.539 | Launch | ||
262,144.0 |
1 | $2.37 | 143.67 | 6.869 | Launch | |
262,144.0 tensor |
4 | $2.89 | 138.92 | 4.832 | Launch | |
262,144.0 tensor |
4 | $3.01 | 4.832 | Launch | ||
262,144.0 tensor |
4 | $3.60 | 4.784 | Launch | ||
262,144.0 |
1 | $3.83 | 133.86 | 6.828 | Launch | |
262,144.0 |
1 | $4.11 | 15.036 | Launch | ||
262,144.0 pipeline |
3 | $4.34 | 9.904 | Launch | ||
262,144.0 tensor |
2 | $4.61 | 52.511 | Launch | ||
262,144.0 |
1 | $4.74 | 42.598 | Launch | ||
262,144.0 tensor |
4 | $5.74 | 14.340 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 125.359 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.