PhoneLLM benchmarks: P95 latency under 600ms, ~$0.0025 per minute
altryne · x · 2026-08-31
Altryy shared performance metrics for PhoneLLM, showing a P95 latency of under 600ms and a cost of approximately a quarter of a cent ($0.0025) per minute. This suggests high cost-efficiency potential for on-device or real-time voice interaction scenarios.
More from Infra
- Qwen 3.8 Flash Next runs at 3.5 tok/s on mid-range Android phone — dai_app · 2026-08-31
- The Boring Company's sales dilemma: 20x cost advantage but no sales team — PTrubey · 2026-08-31
- Running 182B Qwen on 4080: 8 tok/s via SSD offloading — Desperate-Data-3747 · 2026-08-31
- AI is transforming how energy systems are monitored, maintained and operated — ingliguori · 2026-08-31
- Uber Cuts AI Costs 52% While 10xing Usage via Agentic Workflow — alvelda · 2026-08-31
- 29x Kernel Speedup Yields Only 10% End-to-End Gain Due to Memory Wall — shifu_legend · 2026-08-31