AI article
Don't Assume Your Cloud T4 Runs at Spec: Gemma 4 Decode Falls 7% as the Card Warms
Community description: 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.
Dev.to | Oct 16, 2026 | xbill
Automated excerpt
The card runs at its 70 W power limit the whole time. At 77 °C they buy 1,267. python3 thermal. py soak runs/2026-10-15-first-t4/soak-locked1200-1 --lock 1200 66 C n= 16 median 62. 0 W 68 C n= 19 median 63. 4 W 70 C n= 22 median 64. 0 W 72 C n= 26 median 64. 3 W 74 C n= 23 median 65. 1 W 76 C n= 261 median 65. 7 W 78 C n= 271 median 66. 0 W Same clock, same work, 4. 0 W more at 78 °C than at 66 °C.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.