Skip to content
Andrew Voirol
WorkLogAboutContact
HomeWorkLog

AboutContact

✦ Just one prompt away from figuring it all out.

Wednesday, April 8, 2026gemma-4-benchmarks

Think mode: the counterintuitive results

Gemma 4Think ModeExperiments

Ran Think Mode A/B tests today and the results are not what I expected. On the E2B model, enabling Think Mode on a math task dropped the score from 100% to 20%. On the 26B, it dropped logic from 60% to 20%. My hypothesis: on memory-constrained hardware, the extra tokens consumed by 'thinking' crowd out the tokens needed for a good answer. The model literally thinks itself into a worse response. This is the kind of finding you only get from testing on real hardware with real constraints.

← Previous

10 million downloads and counting

Next →

Dark mode toggle with jelly physics


Andrew Voirol

Builder, hacker, shipper. Currently leaving localhost.

Navigate

WorkBuilder’s LogAboutContactRSS Feed

Connect

X / TwitterGitHubLinkedIn

© 2026 Andrew Voirol✦Just one prompt away from figuring it all out.