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
61–80 / 90
1,303.737
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 236
- sample size
- 2082
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1291.2081087642766
- confidence upper
- 1316.2650803736556
Original result ↗1,303.661
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 237
- sample size
- 4352
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1294.5505519452934
- confidence upper
- 1312.7714739667251
Original result ↗1,332.26
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Expert
- dimension
- style
- metric
- Arena rating
- rank
- 238
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1313.5010578716976
- confidence upper
- 1351.018468634465
Original result ↗1,217.778
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Korean
- dimension
- style
- metric
- Arena rating
- rank
- 243
- sample size
- 238
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1176.8619060332453
- confidence upper
- 1258.6945038308922
Original result ↗1,343.787
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Chinese
- dimension
- style
- metric
- Arena rating
- rank
- 245
- sample size
- 1322
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1327.3811587706034
- confidence upper
- 1360.1936913721115
Original result ↗1,300.347
- source id
- lmarena
- leaderboard name
- LMArena Text Longer Query
- dimension
- general
- metric
- Arena rating
- rank
- 251
- sample size
- 4023
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1290.7362725925043
- confidence upper
- 1309.9581167844794
Original result ↗1,351.829
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 252
- sample size
- 3338
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1341.3200217468097
- confidence upper
- 1362.337319236062
Original result ↗1,283.819
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Writing And Literature And Language
- dimension
- general
- metric
- Arena rating
- rank
- 253
- sample size
- 3557
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1273.6340708384037
- confidence upper
- 1294.0043911260873
Original result ↗1,354.918
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 254
- sample size
- 5198
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1346.4206363268106
- confidence upper
- 1363.4146958872625
Original result ↗1,269.674
- source id
- lmarena
- leaderboard name
- LMArena Text Creative Writing
- dimension
- general
- metric
- Arena rating
- rank
- 254
- sample size
- 2389
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1257.1479825886631
- confidence upper
- 1282.199982144342
Original result ↗1,318.117
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Business And Management And Financial Operations
- dimension
- style
- metric
- Arena rating
- rank
- 256
- sample size
- 2999
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1307.2274817564703
- confidence upper
- 1329.0057968500728
Original result ↗1,343.009
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control English
- dimension
- style
- metric
- Arena rating
- rank
- 260
- sample size
- 6439
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1335.100313061393
- confidence upper
- 1350.9180623423608
Original result ↗1,361.113
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 261
- sample size
- 3313
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1350.8120594721224
- confidence upper
- 1371.4140736821587
Original result ↗1,325.447
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts
- dimension
- style
- metric
- Arena rating
- rank
- 270
- sample size
- 8331
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1318.319819213002
- confidence upper
- 1332.5745941352827
Original result ↗1,254.53
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Exclude Ties
- dimension
- style
- metric
- Arena rating
- rank
- 275
- sample size
- 11092
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1246.4330972741186
- confidence upper
- 1262.6259436414725
Original result ↗1,313.775
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Overall
- dimension
- style
- metric
- Arena rating
- rank
- 276
- sample size
- 15663
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1308.2833016837435
- confidence upper
- 1319.2672370956002
Original result ↗1,285.81
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Non English
- dimension
- style
- metric
- Arena rating
- rank
- 280
- sample size
- 9224
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1279.017922948207
- confidence upper
- 1292.601745625671
Original result ↗1,291.191
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Instruction Following
- dimension
- style
- metric
- Arena rating
- rank
- 281
- sample size
- 4352
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1281.9350970892565
- confidence upper
- 1300.4470500435013
Original result ↗1,304.736
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 282
- sample size
- 1012
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1285.237684229689
- confidence upper
- 1324.2335459400445
Original result ↗1,289.415
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 286
- sample size
- 2622
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1277.4829287791463
- confidence upper
- 1301.3461592479284
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