Don't Assume Your Cloud T4 Runs at Spec: Gemma 4 Decode Falls 7% as the Card Warms
8.1 relevance
Score Breakdown
technical depth 9
novelty 8
actionability 8
community 6
strategic 7
personal 9
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Detailed GPU thermal performance analysis for AI inference, highly technical and actionable.
Summary
The same Tesla T4 on the same Google Cloud VM decoded Gemma 4 E2B at 115 tokens/s at 45 °C and 107 at 77 °C. The card sits at its 70 W limit, a hotter chip draws more power at the same clock, so the clock drops. No thermal throttle fires, and no spec sheet mentions it.