How fast is Qwen3.5 2B on the iPhone 14?

About 19 tokens per second, much faster than reading. The first word arrives after 3.2 seconds.

19tokens per second

Much faster than reading

First word in 3.2 s · a 300-word answer in about 25 s

What 19 tokens per second looks like

Typical range 15–21 tokens per second · 17 iPhones

A15 Bionic · 6 GB

Qwen3.5 2B on other iPhones

  1. iPhone 17 Pro MaxFirst word 1.2 s · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-0651tok/s
  2. iPhone 17First word 0.9 s · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-0642tok/s
  3. iPhone 16 ProFirst word 2.1 s · 13 iPhones · 90-day sample: 2026-08-08 to 2026-11-0635tok/s
  4. iPhone 16First word 2.5 s · 10 iPhones · 90-day sample: 2026-08-08 to 2026-11-0633tok/s
  5. iPhone 15 ProFirst word 2.2 s · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-0631tok/s
  6. iPhone 14 ProFirst word 2.9 s · 10 iPhones · 90-day sample: 2026-08-08 to 2026-11-0626tok/s
  7. iPhone 15First word 2.9 s · 21 iPhones · 90-day sample: 2026-08-08 to 2026-11-0626tok/s
  8. iPhone 14 Pro MaxFirst word 3.0 s · 12 iPhones · 90-day sample: 2026-08-08 to 2026-11-0625tok/s
  9. iPhone 14First word 3.2 s · 17 iPhones19tok/s
  10. iPhone 12 ProFirst word 5.1 s · 12 iPhones · 90-day sample: 2026-08-08 to 2026-11-0617tok/s
  11. iPhone 13 Pro MaxFirst word 2.6 s · 10 iPhones · 90-day sample: 2026-08-08 to 2026-11-0617tok/s
  12. iPhone 12First word 4.9 s · 15 iPhones16tok/s
  13. iPhone 13 ProFirst word 2.7 s · 11 iPhones15tok/s
  14. iPhone 13First word 3.9 s · 46 iPhones15tok/s

Other models on the iPhone 14

  1. Gemma 4 E2BFirst word 3.4 s · 13 iPhones · 90-day sample: 2026-08-08 to 2026-11-0628tok/s

Run Qwen3.5 2B on your iPhone

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

Download for iPhone

30-day results and labeled 90-day samples, 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. On phones, four characters of text count as one token for every model; on a Mac, Loci counts the model's own tokens. 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.
  • Results use the last 30 days when enough devices have been measured. Otherwise, labeled 90-day samples include older measurements under the same sample and app-version requirements.
  • Each phone speed comes from at least 10 phones of that model. Different phone models and Android chip variants are measured separately. Open a result to see its sample size.
  • On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.

Methods, fixed editions and citations · Check model requirements for your device