Ctrl K
Back to models

NVIDIA

Nemotron 3 Nano Omni 30B A3B Reasoning

  • Released
  • Open weights
  • NVIDIA Open Model License Agreement
Compare
Intelligence Index

Reasoning setting

10.3
Estimated · Artificial Analysis v4.3.2
Context window
256K tok

Performance profile

ReasoningRank #97 of 107
46.9%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
10.3

Pricing & access

No API offering listed in our tracked sources.

Run locally

GGUF
Context
Estimated memory

~25.2 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

32 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
22.8 GiB
Context + state
95.6 MiB16-bit cache
App allowance
2.3 GiB
Disk space
~34 GBIncludes image file
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/lmstudio-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter lmstudio-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF, choose Q4_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

Images need extra memoryvLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Nemotron 3 Nano Omni 30B A3B Reasoning · Reasoning#113 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 110Phi-4 Multimodal InstructStandard5.0%
  6. 111Llama 4 MaverickStandard4.9%
  7. 112NVIDIA Nemotron Nano 9B V2Reasoning4.9%
  8. 113Nemotron 3 Nano Omni 30B A3B ReasoningReasoning4.8%
  9. 114Qwen3 Omni 30B A3B InstructStandard4.6%
  10. 114Nova MicroStandard4.6%
  11. 114Ministral 3 14BStandard4.6%

Peers use their best measured result on this benchmark.