mistralai

Mistral-Medium-3.5-128B

Hugging Face

vLLM 0.32.0

NVIDIA B300 x1 · tp1 × pp1
ShareLinkedInX
Speed per user (c=1)
41.2tok/s
Time to first token
188ms
Peak throughput
1,618tok/s @ 128
Per GPU at peak
1,618tok/s
Cold start
476s
Context tested
8,192tokens

Measured 10 Nov 2026 · Throughput sweep

SGLang 0.5.22

NVIDIA B300 x1 · tp1 × pp1
ShareLinkedInX
Speed per user (c=1)
40.9tok/s
Time to first token
137ms
Peak throughput
1,735tok/s @ 256
Per GPU at peak
1,735tok/s
Cold start
121s
Context tested
8,192tokens

Measured 10 Nov 2026 · Throughput sweep

ModelPerf Pro

What Mistral-Medium-3.5-128B 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