google

gemma-4-31B-it

Hugging Face

SGLang 0.5.22

NVIDIA B300 x1 · tp1 × pp1
ShareLinkedInX
Speed per user (c=1)
82.4tok/s
Time to first token
63ms
Peak throughput
2,883tok/s @ 128
Per GPU at peak
2,883tok/s
Cold start
126s
Context tested
8,192tokens

Measured 9 Nov 2026 · Throughput sweep

vLLM 0.32.0

NVIDIA B300 x1 · tp1 × pp1
ShareLinkedInX
Speed per user (c=1)
77.2tok/s
Time to first token
64ms
Peak throughput
3,374tok/s @ 256
Per GPU at peak
3,374tok/s
Cold start
171s
Context tested
8,192tokens

Measured 9 Nov 2026 · Throughput sweep

ModelPerf Pro

What gemma-4-31B-it costs to run, per token and per watt

  • Cost per million tokens for every model, engine and GPU
  • Energy per million tokens, tokens per watt and GPU power draw
  • Full concurrency curves for all three workload scenarios
  • Unlimited ROI and break-even calculations with PDF export
  • CSV export of the full leaderboard, paid metrics included
  • New models and re-runs included as they are published
$39 / month, billed annually

or $49 month to month

Get ModelPerf ProSign in to buy · $10Compare plans