Nemotron 3 Nano Omni
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning- NVIDIA
- Family · Nemotron 3 Nano Omni
- Open weights
- Text · Audio · Image · Video → Text
- Tools · Vision
Not on OSMEXO yet
Spec & list price
Context250K
Max output64K
List priceFree
Usage
Tokens / day20.1B▲ 27% 7d
Usage rank#72
Requests / day472
Tool calls / req0.35
Per request · 30 days
Avg input13.7Kabout median
Avg output8271.2× median
Cache hit63%0.9× median
Reasoning share84%1.5× median
Tool-call failures0%0.0× median
Consumption
Peak 10.1M 1 NovLow 2.0M 27 OctRank today #72
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#103/33489 tok/s1.3× faster than median
First token#1020.71 s1.4× quicker than median
Technical details
- Tokenizer
- Other
- License
- other
- Parameters
- 33B
- Moderation
- none
- Downloads · likes
- 115.7K · 443
Request parameters 8
- tools
- tool_choice
- reasoning
- include_reasoning
- temperature
- top_p
- max_tokens
- seed
When to use
Best for
- Audio, video and image understanding
- Multimodal agents with tool calling
- Reasoning over meeting recordings
- Self-hosted multimodal pipelines
Think twice for
- Image or speech generation
- Hardest coding agents
- Structured output enforcement
- New projects (usage is declining)
Research papers
Same family
Nemotron 3 Nano Omni- 10.3
Want Nemotron 3 Nano Omni on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.