▲ TokForge Phone-Speed Leaderboard

How to read this board

Decode t/s

How fast the phone writes its reply, in tokens per second. A token is roughly three quarters of a word. 15 or more feels like comfortable reading speed, 8 to 15 is usable, under 8 feels slow.

Prefill t/s

How fast the phone reads your prompt before it starts answering. Higher means less waiting before the first word appears. A dash means that run did not measure prefill.

Time to first token (TTFT)

The pause between sending a message and seeing the first word of the answer, in milliseconds. Reported by newer app versions through the API.

What counts as a run

Every score comes from the TokForge app's built-in benchmark on a real phone: a fixed prompt, a fixed reply length, several timed passes. The methodology tag on each API row says how the passes were combined (for example "median3" means the median of 3 timed passes). Each row shows the best submitted score for that phone chip, model, backend and quantization combination.

Size classes

Models are grouped by total parameter count: Under 2B, 2-4B (2B up to 5B), 7-9B (5B up to 10B), 14B+ (10B and up). MoE (mixture-of-experts) models get their own tab because only a fraction of their parameters is active per token, so they behave differently from dense models of the same total size. Models we cannot size yet appear under Other.

The signature

Every score is signed by the app before it is sent. That signature is anti-spam friction, not identity verification: it keeps drive-by fake scores off the board and carries no personal data. Submissions hold no user content and nothing that identifies a person.