On-device Android agent with Gemma 4 E2B hits 2.6 tok/s live vs 11 tok/s on replay
HowDevelop · x · 2026-09-07
Developer HowDevelop is building an on-device Android agent using Gemma 4 E2B with Qualcomm QMX kernels. Side note: he spent 5+ hours debugging with GPT-6 Astra on medium, burning 40% of his usage without a confirmed root cause.
The key puzzle: the live agent runs at 2.6 tok/s, while replaying the same request hits 11 tok/s—the gap is unexplained so far.
Related event: Developer Tests On-Device Android Agent with Gemma 4 E2B(2 posts)→
More from coding & agent
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- Morgan Stanley and US banks block third-party AI agents over credentials — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26
- 250 Builders Hack With Codex at Berlin Community Hackathon Ahead of OpenAI DevDay — paw_lean · 2026-10-26