Loci
Jobs

iPhone 16 vs Galaxy S25 Ultra

The iPhone 16 runs Gemma 4 E2B about 2.0 times as fast as the Galaxy S25 Ultra (44 vs 22 tokens per second), but starts answering 2.0 s later.

Every model both run

ModeliPhone 16Galaxy S25 Ultra
Gemma 4 E2B44 tok/sfirst word 2.4 s22 tok/sfirst word 0.5 s
Qwen3.5 2B33 tok/sfirst word 2.6 s16 tok/sfirst word 0.6 s

Every model on the iPhone 16Every model on the Galaxy S25 UltraCompare other devices

Questions
Is the iPhone 16 faster than the Galaxy S25 Ultra for AI?
The iPhone 16 is faster on 2 of the 2 models both run in Loci. The iPhone 16 runs Gemma 4 E2B about 2.0 times as fast as the Galaxy S25 Ultra (44 vs 22 tokens per second), but starts answering 2.0 s later.
Which runs Gemma 4 E2B faster, the iPhone 16 or the Galaxy S25 Ultra?
The iPhone 16 runs Gemma 4 E2B about 2.0 times as fast as the Galaxy S25 Ultra (44 vs 22 tokens per second), but starts answering 2.0 s later.
Which runs Qwen3.5 2B faster, the iPhone 16 or the Galaxy S25 Ultra?
The iPhone 16 runs Qwen3.5 2B about 2.1 times as fast as the Galaxy S25 Ultra (33 vs 16 tokens per second), but starts answering 2.0 s later.

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. 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.
  • Each phone speed comes from at least 10 phones. Fewer Macs run Loci, so each Mac speed says how many Macs it comes from.
  • On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.