How fast is Gemma 4 E2B on the Galaxy S24+?

About 20 tokens per second, much faster than reading. The first word arrives after 1.0 seconds.

20tokens per second

Much faster than reading

First word in 1.0 s · a 300-word answer in about 21 s

What 20 tokens per second looks like

Typical range 15–25 tokens per second · 15 phones

Snapdragon 8 Gen 3 · 12 GB

Gemma 4 E2B on other Android phones

  1. Galaxy S25+First word 0.7 s · 22 phones27tok/s
  2. Galaxy S26First word 0.7 s · 10 phones24tok/s
  3. Galaxy S24+First word 1.0 s · 15 phones20tok/s
  4. Galaxy S25 UltraFirst word 0.6 s · 51 phones18tok/s
  5. Galaxy S26+First word 1.8 s · 11 phones17tok/s
  6. Pixel 10 Pro XLFirst word 0.7 s · 10 phones · 90-day sample: 2026-08-08 to 2026-11-0617tok/s
  7. Pixel 10 ProFirst word 0.8 s · 11 phones · 90-day sample: 2026-08-08 to 2026-11-0617tok/s
  8. Galaxy S25First word 0.4 s · 11 phones16tok/s
  9. Galaxy S26 UltraFirst word 0.6 s · 20 phones16tok/s
  10. Galaxy S25 FEFirst word 1.8 s · 19 phones16tok/s
  11. Galaxy Z Fold7First word 1.3 s · 12 phones · 90-day sample: 2026-08-08 to 2026-11-0615tok/s
  12. Galaxy S24 UltraFirst word 0.8 s · 45 phones15tok/s
  13. Galaxy S23 UltraFirst word 1.5 s · 23 phones14tok/s
  14. Galaxy S23First word 1.2 s · 14 phones14tok/s
  15. POCO X7 ProFirst word 2.0 s · 13 phones13tok/s
  16. Galaxy S24First word 2.4 s · 17 phones12tok/s
  17. Pixel 9 Pro XLFirst word 1.3 s · 11 phones · 90-day sample: 2026-08-08 to 2026-11-0612tok/s
  18. Pixel 10First word 2.2 s · 10 phones · 90-day sample: 2026-08-08 to 2026-11-0611tok/s
  19. Galaxy S22 UltraFirst word 1.6 s · 15 phones9.9tok/s
  20. Pixel 9First word 1.4 s · 11 phones9.2tok/s
  21. Pixel 8First word 1.3 s · 13 phones7.9tok/s

Run Gemma 4 E2B on your phone

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

Get it on Android

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