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
41–60 / 90
1,303.518
- source id
- lmarena
- leaderboard name
- LMArena Text Polish
- dimension
- general
- metric
- Arena rating
- rank
- 200
- sample size
- 531
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1277.0814746338528
- confidence upper
- 1329.9554260231307
Original result ↗1,378.466
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 201
- sample size
- 3313
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1368.2524895939478
- confidence upper
- 1388.6793684482225
Original result ↗1,359.762
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control French
- dimension
- style
- metric
- Arena rating
- rank
- 202
- sample size
- 364
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1328.6391306918822
- confidence upper
- 1390.885581148019
Original result ↗1,345.769
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Business And Management And Financial Operations
- dimension
- general
- metric
- Arena rating
- rank
- 202
- sample size
- 2999
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1335.0629697053562
- confidence upper
- 1356.4753731023382
Original result ↗1,374.869
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 204
- sample size
- 3338
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1364.5035540176632
- confidence upper
- 1385.2341129515985
Original result ↗1,349.054
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Medicine And Healthcare
- dimension
- general
- metric
- Arena rating
- rank
- 214
- sample size
- 1012
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1329.9706571361935
- confidence upper
- 1368.1364835790457
Original result ↗1,348.09
- source id
- lmarena
- leaderboard name
- LMArena Text Overall
- dimension
- general
- metric
- Arena rating
- rank
- 214
- sample size
- 15663
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1342.6900907668041
- confidence upper
- 1353.4895935795957
Original result ↗1,303.439
- source id
- lmarena
- leaderboard name
- LMArena Text Exclude Ties
- dimension
- general
- metric
- Arena rating
- rank
- 214
- sample size
- 11092
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1295.5466069427605
- confidence upper
- 1311.3309651136942
Original result ↗1,320.351
- source id
- lmarena
- leaderboard name
- LMArena Text Non English
- dimension
- general
- metric
- Arena rating
- rank
- 216
- sample size
- 9224
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1313.6608357722516
- confidence upper
- 1327.041238421364
Original result ↗1,352.433
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 217
- sample size
- 2532
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1340.519089037331
- confidence upper
- 1364.346315356623
Original result ↗1,348.097
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts
- dimension
- general
- metric
- Arena rating
- rank
- 217
- sample size
- 8331
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1341.0700303689882
- confidence upper
- 1355.124551485792
Original result ↗1,336.716
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Spanish
- dimension
- style
- metric
- Arena rating
- rank
- 217
- sample size
- 355
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1304.6272609284797
- confidence upper
- 1368.804858141597
Original result ↗1,305.077
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 218
- sample size
- 293
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1270.7388505530766
- confidence upper
- 1339.4156067025222
Original result ↗1,341.364
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 220
- sample size
- 1218
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1324.7663371157782
- confidence upper
- 1357.9626185069612
Original result ↗1,346.882
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 221
- sample size
- 1006
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1328.5944849326552
- confidence upper
- 1365.1694415326338
Original result ↗1,230.797
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Japanese
- dimension
- style
- metric
- Arena rating
- rank
- 221
- sample size
- 144
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1178.7397344354604
- confidence upper
- 1282.854985433484
Original result ↗1,352.755
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 222
- sample size
- 722
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1331.090476938824
- confidence upper
- 1374.4199128657053
Original result ↗1,294.444
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Entertainment And Sports And Media
- dimension
- general
- metric
- Arena rating
- rank
- 227
- sample size
- 2930
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1283.370526931669
- confidence upper
- 1305.5171593021505
Original result ↗1,258.343
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Polish
- dimension
- style
- metric
- Arena rating
- rank
- 235
- sample size
- 531
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1231.7231554388763
- confidence upper
- 1284.9629822332881
Original result ↗1,319.311
- source id
- lmarena
- leaderboard name
- LMArena Text Multi Turn
- dimension
- general
- metric
- Arena rating
- rank
- 236
- sample size
- 2622
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
- confidence lower
- 1307.4853102476964
- confidence upper
- 1331.136272059854
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