Skip to content
Model Pareto

NVIDIA Nemotron Nano 12B v2 VL

NVIDIAOpen weightsartificialanalysis.ai ↗
Input
$0.20/M tok
Output
$0.60/M tok
Blended
$0.30/M tok · 3:1
Speed
201tok/s
Context
128Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: NVIDIA Nemotron Nano 12B v2 VL (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× B200 180GB
BF16 weights
Throughput
~8,216 tok/s
many requests batched
Price
$0.11–0.95 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~200 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (12.6B params) + 25% KV-cache headroom ≈ 32 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~8,216 output tok/s aggregate at batch 235 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~42,188 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

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2NVIDIA Nemotron Nano 12B v2 VLEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~last of 12 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #11Gemini 3.5 Flash-Lite74.5%
  4. ~#12NVIDIA Nemotron Nano 12B v2 VLEstimated<74.5%
No published score — estimated from related benchmarks
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8NVIDIA Nemotron Nano 12B v2 VLEstimated<75.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #24Mistral Large 39.0%
  4. ~#25NVIDIA Nemotron Nano 12B v2 VLEstimated<9.0%
No published score — estimated from related benchmarks

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 Nano 12B v2 VLEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
~#60 of 92 (estimated)~713 Elo
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #59Claude Haiku 4.5719
  4. ~#60NVIDIA Nemotron Nano 12B v2 VLEstimated713
  5. #60MiniCPM5-2B694
No published score — estimated from related benchmarks