zai-org

GLM-5.3-Flash

Hugging Face

SGLang 0.5.22

NVIDIA B300 x2 · tp2 × pp1
ShareLinkedInX
Speed per user (c=1)
172tok/s
Time to first token
76ms
Peak throughput
3,962tok/s @ 256
Per GPU at peak
1,981tok/s
Cold start
599s
Context tested
8,192tokens

Measured 9 Nov 2026 · Throughput sweep

vLLM 0.32.0

NVIDIA B300 x2 · tp2 × pp1
ShareLinkedInX
Speed per user (c=1)
159.3tok/s
Time to first token
63ms
Peak throughput
6,375tok/s @ 256
Per GPU at peak
3,188tok/s
Cold start
777s
Context tested
8,192tokens

Measured 9 Nov 2026 · Throughput sweep

ModelPerf Pro

What GLM-5.3-Flash 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