NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
nvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 262144
- Published model ID
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Evaluations
21–40 / 90
1,402.099
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts English
- dimension
- factuality
- metric
- Arena rating
- rank
- 166
- sample size
- 2165
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1389.5009053950305
- confidence upper
- 1414.697556529343
Original result ↗1,311.92
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Writing And Literature And Language
- dimension
- factuality
- metric
- Arena rating
- rank
- 167
- sample size
- 2308
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1300.0123518883836
- confidence upper
- 1323.8276426122834
Original result ↗1,391.314
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality English
- dimension
- factuality
- metric
- Arena rating
- rank
- 170
- sample size
- 5938
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1383.6192106258093
- confidence upper
- 1399.0091097676263
Original result ↗1,376.874
- source id
- lmarena
- leaderboard name
- LMArena Text Spanish
- dimension
- general
- metric
- Arena rating
- rank
- 170
- sample size
- 355
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1345.3273618013498
- confidence upper
- 1408.4210771616395
Original result ↗1,330.976
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Instruction Following
- dimension
- factuality
- metric
- Arena rating
- rank
- 170
- sample size
- 2969
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1319.7365802890358
- confidence upper
- 1342.2162225502116
Original result ↗1,402.695
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Software And It Services
- dimension
- factuality
- metric
- Arena rating
- rank
- 171
- sample size
- 3962
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1393.197344781708
- confidence upper
- 1412.1919115171195
Original result ↗1,338.225
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Longer Query
- dimension
- factuality
- metric
- Arena rating
- rank
- 172
- sample size
- 2780
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1327.106361515609
- confidence upper
- 1349.3431624613406
Original result ↗1,348.47
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 179
- sample size
- 293
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1314.3199124266093
- confidence upper
- 1382.620227908178
Original result ↗1,376.793
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts
- dimension
- factuality
- metric
- Arena rating
- rank
- 181
- sample size
- 8112
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1369.8432359465362
- confidence upper
- 1383.7418166348145
Original result ↗1,335.159
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Non English
- dimension
- factuality
- metric
- Arena rating
- rank
- 181
- sample size
- 9019
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1328.4668317791525
- confidence upper
- 1341.8509679478664
Original result ↗1,329.07
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Exclude Ties
- dimension
- factuality
- metric
- Arena rating
- rank
- 181
- sample size
- 10840
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1321.875841501846
- confidence upper
- 1336.2641451855047
Original result ↗1,362.125
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Overall
- dimension
- factuality
- metric
- Arena rating
- rank
- 182
- sample size
- 15356
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1356.875627170003
- confidence upper
- 1367.3752005460574
Original result ↗1,265.751
- source id
- lmarena
- leaderboard name
- LMArena Text Japanese
- dimension
- general
- metric
- Arena rating
- rank
- 183
- sample size
- 144
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1213.3656254014518
- confidence upper
- 1318.1364863882968
Original result ↗1,373.329
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 193
- sample size
- 722
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1351.8324694773355
- confidence upper
- 1394.824834445656
Original result ↗1,269.857
- source id
- lmarena
- leaderboard name
- LMArena Text Korean
- dimension
- general
- metric
- Arena rating
- rank
- 193
- sample size
- 238
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1229.5868663737458
- confidence upper
- 1310.1271428536932
Original result ↗1,385.003
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 194
- sample size
- 1322
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1368.8893084337237
- confidence upper
- 1401.116943152755
Original result ↗1,370.52
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 196
- sample size
- 1006
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1352.4154423484304
- confidence upper
- 1388.6249753199634
Original result ↗1,382.162
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 199
- sample size
- 5198
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1373.7789255328705
- confidence upper
- 1390.5444174822217
Original result ↗1,377.202
- source id
- lmarena
- leaderboard name
- LMArena Text English
- dimension
- general
- metric
- Arena rating
- rank
- 200
- sample size
- 6439
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1369.4166725350965
- confidence upper
- 1384.9881671047474
Original result ↗1,355.386
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 200
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1336.931262633496
- confidence upper
- 1373.8413914169992
Original result ↗Published prices
1–5 / 5
$0.05
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.20
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.06
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.24
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–3 / 3
- source model id
- HuggingFace/nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16@1
- hosting
- foundry-managed-compute
- license
- nvidia-open-model-license
- source model id
- publishers/hf-nvidia/models/nvidia-nemotron-3-nano-30b-a3b-bf16@001
- hosting
- vertex-self-deployed
- source model id
- publishers/nvidia/models/nemotron-v3@nemotron-3-nano-30b-a3b-bf16
- hosting
- vertex-self-deployed
Source specification observations
1–2 / 2
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 235929
- normalized value
- 235929
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 1509547
- likes
- 840
- pipeline tag
- text-generation
- library name
- transformers
- License
- other
Explore more models