NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
NVIDIABenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1348
- Among open models
- #68of 148
- Among all on Arena
- #214
- Votes
- 15,658
Measured on NVIDIA-Nemotron-3-Nano-30B-A3B (BF16), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- French1396#49#160364
- Chinese1385#63#1951.3K
- Software & IT1382#64#1995.2K
- Coding1378#66#2013.3K
- English1377#64#2006.4K
- Spanish1377#55#171355
- Hard prompts, English1375#66#2043.3K
- Applied math1374#60#194714
- Math1370#61#1961K
- Expert1355#65#2001K
- Science1352#70#2172.5K
- Medicine & health1349#67#2141K
- German1348#54#179293
- Hard prompts1348#69#2178.3K
- Business & finance1346#67#2033K
- Legal & government1342#69#2191.2K
- Non-English1320#69#2169.2K
- Multi-turn1319#77#2362.6K
- Instructions1304#77#2374.3K
- Russian1304#75#2362.1K
- Polish1304#59#199531
- Excluding ties1303#68#21411.1K
- Long prompts1300#83#2514K
- Media & sports1295#73#2272.9K
- Writing & literature1284#81#2533.6K
- Creative writing1270#82#2542.4K
- Korean1270#55#192238
- Japanese1266#52#183144
| Model | Params | Score |
|---|---|---|
| 4.0B | — | |
| 31.6B | 1348 |
About as strong, smaller
Compare
gemma-3-12b-itGoogle133412.2B
BenchClub runs
No runs yet
Be the first to benchmark NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 on your own hardware.
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Nemotron-3-Nano-30B-A3B-GGUF38 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-OptiQ-4bit12 builds
- AWQ · vLLM, SGLangcybermotaz/nemotron3-nano-nvfp4-w4a162 builds
- GPTQ · vLLM, SGLangTevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ1 build
Most downloaded
- NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4nvidia · Quantization600.3K downloads
- NVIDIA-Nemotron-3-Nano-30B-A3B-FP8nvidia · Quantization160.7K downloads
- Nemotron-3-Nano-30B-A3B-GGUFunsloth · Quantization40.3K downloads
- NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitlmstudio-community · Fine-tune31.1K downloads
- NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitlmstudio-community · Fine-tune28K downloads
More from NVIDIA
See moreOther 20–40B models
See more
Qwen3.8-27BQwen6.9M27.8B

gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
GLM-4.7-FlashZ.ai1.2M31.2B