Skip to content

NVIDIA · Model profile

Nemotron 3 Nano Omni 30B A3B Reasoning

Intelligence, Performance & Price Analysis

Source: Canonical slug: nemotron-3-nano-omni-30b-a3b · Canonical model registry at build time

Routing verdict

Capable everyday model

Good for routine tasks; route complex reasoning and premium workloads to stronger models.

Nemotron 3 Nano Omni 30B A3B Reasoning summary metrics

Intelligence
15 scoreNemotron 3 Nano Omni 30B A3B Reasoning scores 15 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Speed
279.0 output tokens/secNemotron 3 Nano Omni 30B A3B Reasoning generates output at 279.0 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 101.0 t/s).
Latency
1.04s TTFTNemotron 3 Nano Omni 30B A3B Reasoning has a time to first token (TTFT) of 1.04s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).
Input Price
$0.07 / 1M tokensNemotron 3 Nano Omni 30B A3B Reasoning costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.30 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
Output Price
$0.30 / 1M tokensNemotron 3 Nano Omni 30B A3B Reasoning costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.30 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.

Assessment

Routing verdict and task fit

Nemotron 3 Nano Omni 30B A3B Reasoning scores 15 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Nemotron 3 Nano Omni 30B A3B Reasoning generates output at 279.0 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 101.0 t/s). Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.30 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
Task fit assessment
WorkloadRatingNotes
Complex reasoning & agentic workflowsViableIntelligence score 15 handles routine reasoning but may struggle with open-ended agentic tasks.
High-volume chat & customer-facingOptimalOutput speed 279.0 tokens/sec and capable intelligence make this suitable for real-time chat at scale.
Latency-sensitive applicationsOptimalTTFT 1.04s — adequate latency for most interactive use cases.
Cost-sensitive pipelinesOptimalOutput pricing at $0.30 is very competitive for high-volume workloads.

Evidence

Evidence charts

16 published comparison charts for this profile. Nemotron 3 Nano Omni 30B A3B Reasoning is marked with a diamond and bold label; each chart has a table view and lists its source and retrieval date.

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 20 models.
  1. Claude Fable 5 (with fallback)40.1
  2. Gemini 3.5 Flash22.7
  3. GPT-5.5 (xhigh)20.1
  4. Grok 4.3 (high)18.3
  5. Kimi K2.66.4
  6. Muse Spark4.1
  7. GLM-5.2 (max)4
  8. MiniMax-M31.4
  9. Nemotron 3 Ultra-0.833
  10. DeepSeek V4 Pro (max)-10
  11. Qwen3.6 27B-19.8
  12. Qwen3.6 35B A3B-21.4
  13. Gemma 4 31B-45.4
  14. Gemma 4 26B A4B-48.1
  15. gpt-oss-120b (high)-50
  16. Mistral Small 3.1-50.3
  17. Qwen3 32B-50.5
  18. NVIDIA Nemotron 3 Nano-51.6
  19. Qwen3.5 9B-52.5
  20. Qwen3.6 27B-52.8

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 14.9, row 19 of 20 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. Qwen3.6 27B37.1
  12. Qwen3.6 35B A3B31.6
  13. Qwen3.6 27B30.5
  14. Gemma 4 31B29.4
  15. Gemma 4 26B A4B25.7
  16. gpt-oss-120b (high)23.8
  17. Qwen3.5 9B21.4
  18. Devstral Small 217.4
  19. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)14.9
  20. gpt-oss-20b (high)14.9

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 14.9, row 19 of 20 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. Qwen3.6 27B37.1
  12. Qwen3.6 35B A3B31.6
  13. Qwen3.6 27B30.5
  14. Gemma 4 31B29.4
  15. Gemma 4 26B A4B25.7
  16. gpt-oss-120b (high)23.8
  17. Qwen3.5 9B21.4
  18. Devstral Small 217.4
  19. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)14.9
  20. gpt-oss-20b (high)14.9

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis

16 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 16 models.
  1. Nemotron 3 Ultra83.3
  2. NVIDIA Nemotron 3 Nano83.3
  3. DeepSeek V4 Pro (max)50
  4. Magistral Small 1.250
  5. GLM-5.2 (max)44.4
  6. Qwen3 30B A3B 250744.4
  7. gpt-oss-120b (high)38.9
  8. Qwen3.6 27B38.9
  9. Qwen3.6 35B A3B38.9
  10. Qwen3.6 27B38.9
  11. Gemma 4 31B38.9
  12. Gemma 4 26B A4B38.9
  13. Qwen3.5 9B38.9
  14. gpt-oss-20b (high)38.9
  15. Kimi K2.633.3
  16. MiniMax-M333.3

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Intelligence

Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis

12 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 14.9, row 12 of 12 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. gpt-oss-120b (high)23.8
  12. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)14.9

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Output Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 279 t/s, row 2 of 20 in the published order.
  1. gpt-oss-120b (high)314 t/s
  2. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)279 t/s
  3. Nemotron 3 Ultra250 t/s
  4. GLM-5.2 (max)218 t/s
  5. gpt-oss-20b (high)195 t/s
  6. Gemini 3.5 Flash192 t/s
  7. Mistral Small 3.1171 t/s
  8. Qwen3.6 35B A3B166 t/s
  9. Grok 4.3 (high)164 t/s
  10. Qwen3 30B A3B 2507131 t/s
  11. NVIDIA Nemotron 3 Nano110 t/s
  12. MiniMax-M399 t/s
  13. Qwen3 32B93 t/s
  14. GPT-5.5 (xhigh)88 t/s
  15. Magistral Small 1.280 t/s
  16. Ministral 3 14B78 t/s
  17. Kimi K2.676 t/s
  18. DeepSeek V4 Pro (max)72 t/s
  19. Claude Fable 5 (with fallback)71 t/s
  20. Devstral Small 268 t/s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Output speed context
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.

Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

11 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 279 t/s, row 2 of 11 in the published order.
  1. gpt-oss-120b (high)314 t/s
  2. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)279 t/s
  3. Nemotron 3 Ultra250 t/s
  4. GLM-5.2 (max)218 t/s
  5. Gemini 3.5 Flash192 t/s
  6. Grok 4.3 (high)164 t/s
  7. MiniMax-M399 t/s
  8. GPT-5.5 (xhigh)88 t/s
  9. Kimi K2.676 t/s
  10. DeepSeek V4 Pro (max)72 t/s
  11. Claude Fable 5 (with fallback)71 t/s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Output speed context
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 1.79 s, row 5 of 20 in the published order.
  1. Mistral Small 3.12.92 s
  2. Ministral 3 14B6.4 s
  3. Devstral Small 27.37 s
  4. gpt-oss-120b (high)1.59 s
  5. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)1.79 s
  6. Qwen3.6 27B8.34 s
  7. Nemotron 3 Ultra2 s
  8. GLM-5.2 (max)2.3 s
  9. gpt-oss-20b (high)2.56 s
  10. Qwen3 30B A3B 25073.8 s
  11. NVIDIA Nemotron 3 Nano4.55 s
  12. Grok 4.3 (high)3.05 s
  13. MiniMax-M35.05 s
  14. Qwen3 32B5.37 s
  15. Gemini 3.5 Flash2.6 s
  16. Magistral Small 1.26.24 s
  17. Qwen3.6 35B A3B3.02 s
  18. Qwen3.5 9B8.41 s
  19. Gemma 4 31B14.57 s
  20. Kimi K2.66.56 s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 7.17 s, row 6 of 20 in the published order.
  1. Mistral Small 3.10 s
  2. Ministral 3 14B0 s
  3. Devstral Small 20 s
  4. Qwen3.6 27B0 s
  5. gpt-oss-120b (high)6.37 s
  6. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)7.17 s
  7. Nemotron 3 Ultra9.09 s
  8. GLM-5.2 (max)9.19 s
  9. gpt-oss-20b (high)10.24 s
  10. Qwen3 30B A3B 250715.22 s
  11. NVIDIA Nemotron 3 Nano18.21 s
  12. Grok 4.3 (high)0 s
  13. MiniMax-M320.19 s
  14. Qwen3 32B21.47 s
  15. Magistral Small 1.224.97 s
  16. Gemini 3.5 Flash0 s
  17. Qwen3.6 35B A3B32.57 s
  18. Qwen3.5 9B33.66 s
  19. Gemma 4 31B50.59 s
  20. Kimi K2.658.43 s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Latency considerations
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.

Context Window

Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning: 256k, row 16 of 20 in the published order.
  1. Gemini 3.5 Flash1M
  2. Claude Fable 5 (with fallback)1M
  3. GLM-5.2 (max)1M
  4. DeepSeek V4 Pro (max)1M
  5. Grok 4.3 (high)1M
  6. MiniMax-M31M
  7. NVIDIA Nemotron 3 Nano1M
  8. GPT-5.5 (xhigh)922k
  9. Nemotron 3 Ultra262.1k
  10. Muse Spark262.1k
  11. Qwen3.6 27B262.1k
  12. Qwen3.6 35B A3B262.1k
  13. Qwen3.6 27B262.1k
  14. Qwen3.5 9B262.1k
  15. Qwen3 30B A3B 2507262.1k
  16. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)256k
  17. Kimi K2.6256k
  18. Gemma 4 31B256k
  19. Gemma 4 26B A4B256k
  20. Devstral Small 2256k

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Context window sizing
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 20 models.
  1. gpt-oss-20b (high)0.000555
  2. NVIDIA Nemotron 3 Nano0.000622
  3. Gemma 4 26B A4B0.00194
  4. Mistral Small 3.10.00143
  5. DeepSeek V4 Pro (max)0.0063
  6. gpt-oss-120b (high)0.00454
  7. Qwen3 30B A3B 25070.00466
  8. MiniMax-M30.0139
  9. Grok 4.3 (high)0.0101
  10. Ministral 3 14B0.00235
  11. Qwen3.5 9B0.00178
  12. Qwen3.6 35B A3B0.0213
  13. Nemotron 3 Ultra0.0209
  14. Magistral Small 1.20.00704
  15. Qwen3.6 27B0.0251
  16. Kimi K2.60.0216
  17. Qwen3.6 27B0.041
  18. GLM-5.2 (max)0.0268
  19. Gemini 3.5 Flash0.0884
  20. GPT-5.5 (xhigh)0.107

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis

10 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 10 models.
  1. DeepSeek V4 Pro (max)$0.045
  2. gpt-oss-120b (high)$0.061
  3. MiniMax-M3$0.125
  4. Grok 4.3 (high)$0.139
  5. Nemotron 3 Ultra$0.244
  6. Kimi K2.6$0.346
  7. GLM-5.2 (max)$0.370
  8. Gemini 3.5 Flash$0.586
  9. GPT-5.5 (xhigh)$0.863
  10. Claude Fable 5 (with fallback)$2.75

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 20 models.
  1. gpt-oss-20b (high)0.795
  2. Mistral Small 3.11.5
  3. NVIDIA Nemotron 3 Nano0.658
  4. Gemma 4 26B A4B2.3
  5. gpt-oss-120b (high)3.5
  6. Ministral 3 14B3
  7. Qwen3 30B A3B 25077.6
  8. DeepSeek V4 Pro (max)7.2
  9. Qwen3.5 9B2.6
  10. MiniMax-M314.5
  11. Grok 4.3 (high)12.5
  12. Magistral Small 1.28.2
  13. Qwen3.6 35B A3B164.7
  14. Qwen3.6 27B87.9
  15. Nemotron 3 Ultra33.5
  16. Qwen3.6 27B28
  17. GLM-5.2 (max)32.9
  18. Kimi K2.625
  19. Gemini 3.5 Flash114
  20. GPT-5.5 (xhigh)131.8

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis

20 models; segments: Input, Output, Cache Hit. Nemotron 3 Nano Omni 30B A3B Reasoning: $0.375, row 4 of 20 in the published order.
  • Input
  • Output
  • Cache Hit
  1. Qwen3.5 9B$0.250
  2. gpt-oss-20b (high)$0.250
  3. NVIDIA Nemotron 3 Nano$0.250
  4. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)$0.375
  5. Mistral Small 3.1$0.400
  6. Ministral 3 14B$0.400
  7. Gemma 4 26B A4B$0.615
  8. gpt-oss-120b (high)$0.900
  9. DeepSeek V4 Pro (max)$1.31
  10. MiniMax-M3$1.56
  11. Qwen3.6 35B A3B$1.73
  12. Magistral Small 1.2$2.00
  13. Qwen3 30B A3B 2507$2.60
  14. Nemotron 3 Ultra$3.60
  15. Grok 4.3 (high)$3.95
  16. Qwen3.6 27B$4.20
  17. Qwen3.6 27B$4.20
  18. Kimi K2.6$5.11
  19. GLM-5.2 (max)$6.06
  20. Qwen3 32B$9.10

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis

20 models in the published order. Nemotron 3 Nano Omni 30B A3B Reasoning is not marked in this published set of 20 models.
  1. Mistral Small 3.10.447
  2. Nemotron 3 Ultra1.4
  3. Devstral Small 21.4
  4. Grok 4.3 (high)1.6
  5. gpt-oss-20b (high)1.7
  6. gpt-oss-120b (high)1.9
  7. Magistral Small 1.21.9
  8. Gemini 3.5 Flash2.2
  9. Ministral 3 14B2.2
  10. Qwen3 30B A3B 25072.3
  11. Qwen3.6 35B A3B2.6
  12. GLM-5.2 (max)2.8
  13. Qwen3.6 27B3
  14. GPT-5.5 (xhigh)3
  15. NVIDIA Nemotron 3 Nano3.2
  16. MiniMax-M33.9
  17. Claude Fable 5 (with fallback)4.8
  18. Gemma 4 31B5.5
  19. Qwen3.6 27B6.5
  20. DeepSeek V4 Pro (max)6.8

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis

20 models; segments: Passive Params, Active Params. Nemotron 3 Nano Omni 30B A3B Reasoning: 30B, row 12 of 20 in the published order.
  • Passive Params
  • Active Params
  1. DeepSeek V4 Pro (max)1,600B
  2. Kimi K2.61,000B
  3. GLM-5.2 (max)753B
  4. Nemotron 3 Ultra550B
  5. MiniMax-M3428B
  6. gpt-oss-120b (high)117B
  7. Qwen3.6 35B A3B36B
  8. Qwen3 32B32.8B
  9. NVIDIA Nemotron 3 Nano31.6B
  10. Gemma 4 31B30.7B
  11. Qwen3 30B A3B 250730.5B
  12. Nemotron 3 Nano Omni 30B A3B Reasoning (this model)30B
  13. Qwen3.6 27B27.8B
  14. Qwen3.6 27B27.8B
  15. Gemma 4 26B A4B25.2B
  16. DiffusionGemma 26B A4B25.2B
  17. Devstral Small 224B
  18. Mistral Small 3.124B
  19. Magistral Small 1.224B
  20. gpt-oss-20b (high)21B

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Architecture scale
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.

Specifications

Architecture and limits

Nemotron 3 Nano Omni 30B A3B Reasoning technical specifications
SpecificationValueSource
Model typeOpen weightsfaq
ReasoningYesfaq
Input modalitiesNemotron 3 Nano Omni 30B A3B Reasoning supports text, image, speech, and video input.faq
Output modalitiesNemotron 3 Nano Omni 30B A3B Reasoning supports text output.faq
Context window260k tokensfaq
Open weights / sourceYes, Nemotron 3 Nano Omni 30B A3B Reasoning is open weights. The model weights are publicly available and can be downloaded for self-hosting.faq
ParametersNemotron 3 Nano Omni 30B A3B Reasoning has 30 billion parameters (3 billion active).faq
Active parametersNemotron 3 Nano Omni 30B A3B Reasoning is a Mixture of Experts (MoE) model with 30 billion total parameters, but only 3 billion active parameters are used during inference.faq
LicenseNemotron 3 Nano Omni 30B A3B Reasoning is released under the NVIDIA Open Model License Agreement license. This license allows commercial use.faq
API availabilityYes, Nemotron 3 Nano Omni 30B A3B Reasoning is available via API through 2 providers.faq

Method

Methodology & Provenance

This page is rendered from the normalized profile and page JSON for Nemotron 3 Nano Omni 30B A3B Reasoning.

Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.

Questions

Model FAQ and technical disclosures

Nemotron 3 Nano Omni 30B A3B Reasoning was released on April 29, 2026.

Nemotron 3 Nano Omni 30B A3B Reasoning was created by NVIDIA.

Nemotron 3 Nano Omni 30B A3B Reasoning scores 15 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).

Nemotron 3 Nano Omni 30B A3B Reasoning generates output at 279.0 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 101.0 t/s).

Nemotron 3 Nano Omni 30B A3B Reasoning has a time to first token (TTFT) of 1.04s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).

Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.07 per 1M input tokens (very competitive, median: $0.18) and $0.30 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.

Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.07 per 1M input tokens and $0.30 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.10 per 1M tokens. Pricing may vary by provider.

Yes, Nemotron 3 Nano Omni 30B A3B Reasoning is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Nemotron 3 Nano Omni 30B A3B Reasoning supports text, image, speech, and video input.

Nemotron 3 Nano Omni 30B A3B Reasoning supports text output.

Yes, Nemotron 3 Nano Omni 30B A3B Reasoning supports image input and can analyze, describe, and answer questions about images.

Yes, Nemotron 3 Nano Omni 30B A3B Reasoning is multimodal. It can process text, image, speech, and video input and generate text output.

Nemotron 3 Nano Omni 30B A3B Reasoning has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Nemotron 3 Nano Omni 30B A3B Reasoning is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Nemotron 3 Nano Omni 30B A3B Reasoning has 30 billion parameters (3 billion active).

Nemotron 3 Nano Omni 30B A3B Reasoning is a Mixture of Experts (MoE) model with 30 billion total parameters, but only 3 billion active parameters are used during inference.

Nemotron 3 Nano Omni 30B A3B Reasoning is released under the NVIDIA Open Model License Agreement license. This license allows commercial use.

Nemotron 3 Nano Omni 30B A3B Reasoning achieves a score of 15 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Nemotron 3 Nano Omni 30B A3B Reasoning is available via API through 2 providers.

Nemotron 3 Nano Omni 30B A3B Reasoning is available through 2 API providers.

Models

  • 01NVIDIAOther NVIDIA models in the catalog.
  • 02LeaderboardsCertified metric ranks, when published.