Skip to content
Model Pareto

NVIDIA Nemotron 3 Nano 4B

NVIDIAOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~190tok/sest.
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: NVIDIA Nemotron 3 Nano 4B. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
1× B200 180GB
BF16 weights
Throughput
~15,832 tok/s
many requests batched
Price
$0.047–0.42 /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)
  • BF16 weights (3.97B params) + 25% KV-cache headroom ≈ 10 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~15,832 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~133,895 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.

Writing & chat

Hard reasoning

Agents

OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3NVIDIA Nemotron 3 Nano 4BEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~39.8%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #20Nemotron 3 Ultra44.4%
  4. ~#21NVIDIA Nemotron 3 Nano 4BEstimated39.8%
  5. #21Mistral Small 421.3%
No published score — estimated from related benchmarks
~#60 of 92 (estimated)~703 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #59Claude Haiku 4.5719
  4. ~#60NVIDIA Nemotron 3 Nano 4BEstimated703
  5. #60MiniCPM5-2B694
No published score — estimated from related benchmarks
~#90 of 91 (estimated)~3.4%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #88Ministral 3 8B3.7%
  4. ~#90NVIDIA Nemotron 3 Nano 4BEstimated3.4%
  5. #90Llama 4 Scout3.3%
No published score — estimated from related benchmarks