Skip to content
Model Pareto

Nemotron Cascade 2 30B A3B

NVIDIAOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~200tok/sest.
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nemotron Cascade 2 30B A3B. 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× H200 141GB
FP8 weights
Throughput
~8,799 tok/s
many requests batched
Price
$0.044–0.37 /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 (30B params, 3B active per token) + 40% KV-cache headroom ≈ 42 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,799 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.

Writing & chat

Hard reasoning

Agents

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. ~#5Nemotron Cascade 2 30B A3BEstimated<47.5%
No published score — estimated from related benchmarks
~#47 of 91 (estimated)~15.6%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #46A.X-K216.1%
  4. ~#47Nemotron Cascade 2 30B A3BEstimated15.6%
  5. #47MiniMax-M315.3%
No published score — estimated from related benchmarks