Loci
Jobs

A15 Bionic · 4–6 GB

iPhone 13

Also iPhone 14, iPhone 13 Pro, iPhone 13 Pro Max, iPhone 14 Plus and iPhone SE (3rd gen), with the same A15 Bionic chip.

Qwen3.5 2B

19tokens per second

Much faster than reading

First word in 3.4 s · a 300-word answer in about 25 s

What 19 tokens per second looks like

Typical range 13–21 tokens per second · 93 iPhones

Slows to 9.7 tokens per second when the iPhone is hot.

Qwen3.5 2B on the iPhone 13

Every model on the iPhone 13

  1. Gemma 4 E2BFirst word 3.0 s · 20 iPhones25tok/s
  2. Qwen3.5 2BFirst word 3.4 s · 93 iPhones19tok/s

Run Qwen3.5 2B on your iPhone

Loci is free, needs no account, and keeps every conversation on your device.

Download for iPhone

Last 30 days, through · updated daily

How these speeds are measured

  • Every number comes from real chats in Loci, timed on the device that wrote the answer, with Loci's default settings.
  • Tokens per second is how fast an answer is written once it starts. Four characters of text count as one token, for every model and device. Reading pace is about 5.
  • First word is how long an answer takes to start after you send a message. Longer conversations take longer.
  • Each device counts once. The large number is the median; the typical range covers the middle half of devices.
  • Answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.