Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b- NVIDIA
- Family · Nemotron 3 Nano
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context256K
Max output236K
Input / 1M$0.06
Output / 1M$0.244× input
Usage
Tokens / day1.3B▲ 33% 7d
Usage rank#187
Requests / day121.1K
Tool calls / req0.18
Per request · 30 days
Avg input4.6K0.3× median
Avg output1.1K1.7× median
Cache hit31%0.4× median
Reasoning share85%1.5× median
Tool-call failures6.8%3.6× median
Consumption
Peak 1.4B 5 OctLow 312.9M 2 OctRank today #187
News & trends
News · latest from NVIDIA
- Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKSAWS · 29 Oct
- NVIDIA Open Models Advance Europe’s Sovereign Intelligence Across IndustriesNVIDIA · 21 Oct
- NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal ReasoningNVIDIA · 15 Oct
- Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt ModelsNVIDIA · 15 Oct
Speed
Output speed#47/334112 tok/s1.8× faster than median
Fastest provider133 tok/sbest of 2 providers
First token#570.53 s2.0× quicker than median
Technical details
- Tokenizer
- Other
- License
- other
- Parameters
- 31.6B
- Moderation
- none
- Downloads · likes
- 1.7M · 840
Request parameters 18
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+8 more
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Cost-sensitive agents with tool calling
- High-volume chat and classification
- Self-hosted deployments using open weights
- Long document question answering
- Low-latency structured extraction
Think twice for
- Hardest reasoning and coding tasks
- Image input
- Image generation
Want Nemotron 3 Nano 30B A3B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.