Skip to content
Model Pareto

NVIDIA Nemotron 3 Nano 30B A3B

NVIDIAOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.05/M tok
Output
$0.20/M tok
Blended
$0.088/M tok · 3:1
Speed
245tok/s
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning). Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× H200 141GB
FP8 weights
Throughput
~8,664 tok/s
many requests batched
Price
$0.045–0.37 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (31.6B params, 3B active per token) + 40% KV-cache headroom ≈ 44 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,664 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

DeepSWE v1.1Estimated
~#29 of 31 (estimated)~41.0%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #28Qwen3.8 27B42.2%
  4. ~#29NVIDIA Nemotron 3 Nano 30B A3BEstimated41.0%
  5. #29Nex-N2.5-Mini36.1%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15NVIDIA Nemotron 3 Nano 30B A3BEstimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5NVIDIA Nemotron 3 Nano 30B A3BEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#51 of 531286 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #50Ring-flash-2.0Few votes1293
  4. #51NVIDIA Nemotron 3 Nano 30B A3B1286
  5. #52Phi-41233
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#51 of 531314 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #50gpt-oss-20b1317
  4. #51NVIDIA Nemotron 3 Nano 30B A3B1314
  5. #52Olmo 3.1 32B Think1286
lmarena.ai · 2026-09-13

Hard reasoning

Agents

OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~58.9%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11NVIDIA Nemotron 3 Nano 30B A3BEstimated58.9%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5NVIDIA Nemotron 3 Nano 30B A3BEstimated<47.5%
No published score — estimated from related benchmarks