NVIDIA Nemotron 3 Nano 4B
- 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
IFBenchVerified
#60 of 13958.2%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #59Ternary Bonsai 27B58.5%
- #60NVIDIA Nemotron 3 Nano 4B58.2%
- #61EXAONE 4.5 33B58.0%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- #4gpt-oss-120b81.3%
- ~#5NVIDIA Nemotron 3 Nano 4BEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#48 of 57 (estimated)~1323 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #47INTELLECT-3Few votes1327
- ~#48NVIDIA Nemotron 3 Nano 4BEstimated1323
- #48Llama 4 Maverick1311
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#49 of 57 (estimated)~1346 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #48Llama 3.1 Nemotron Ultra 253B v1Few votes1348
- ~#49NVIDIA Nemotron 3 Nano 4BEstimated1346
- #49Olmo 3.1 32B Instruct1330
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#20 of 26 (estimated)~1542 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #19Gemini 3.5 Flash-Lite1559
- ~#20NVIDIA Nemotron 3 Nano 4BEstimated1542
- #20DeepSeek V4.1 Flash1540
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#153 of 19251.3%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #153LFM2.5-8B-A1B51.3%
- #153NVIDIA Nemotron 3 Nano 4B51.3%
- #155Llama 3.3 Instruct 70B49.8%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#169 of 1984.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #169Llama 4 Maverick4.9%
- #169NVIDIA Nemotron 3 Nano 4B4.9%
- #171Gemma 4 E4B4.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#24 of 34 (estimated)~36.8%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #23Mistral Large 338.0%
- ~#24NVIDIA Nemotron 3 Nano 4BEstimated36.8%
- #24Devstral 236.7%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#61 of 11928.1%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #60GLM-4.6V30.7%
- #61NVIDIA Nemotron 3 Nano 4B28.1%
- #62Falcon-H1R-7B27.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~52.3%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12NVIDIA Nemotron 3 Nano 4BEstimated52.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~39.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21NVIDIA Nemotron 3 Nano 4BEstimated39.8%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~703 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60NVIDIA Nemotron 3 Nano 4BEstimated703
- #60MiniCPM5-2B694
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.3%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79NVIDIA Nemotron 3 Nano 4BEstimated0.3%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#90 of 91 (estimated)~3.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #88Ministral 3 8B3.7%
- ~#90NVIDIA Nemotron 3 Nano 4BEstimated3.4%
- #90Llama 4 Scout3.3%
No published score — estimated from related benchmarks