On-device AI leaderboard

Top Engines

Mobile: 0 engines ranked

+ 3 engines with incomplete coverage

Coverage

Speed score per device, out of 100: each device ranked on its own.
DesktopMobile
M5 Max 64 GiB macOS 27 Apple M5 MaxOnePlus 13 16 GB Android 16 Qualcomm Snapdragon 8 Elite (SM8750)Pixel 8 8 GB Android 16 Google Tensor G3iPhone 12 4 GB iOS 27 Apple A14 Bionic
llama.cpp85 out of 100, in 22 of 22 comparisons97 out of 100, in 6 of 6 comparisons86 out of 100, in 4 of 4 comparisons69 out of 100, in 5 of 5 comparisons
LiteRT-LMNot ranked. Results in 4 of 22 comparisons; a rank needs 11.78 out of 100, in 4 of 6 comparisons98 out of 100, in 3 of 4 comparisonsNot measured on this device.
uzuNot ranked. Results in 7 of 22 comparisons; a rank needs 11.Not measured on this device.Not measured on this device.100 out of 100, in 5 of 5 comparisons
Magnitude91 out of 100, in 12 of 22 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM98 out of 100, in 18 of 22 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama88 out of 100, in 22 of 22 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX98 out of 100, in 12 of 22 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ExecuTorchNot ranked. Results in 2 of 22 comparisons; a rank needs 11.Not ranked. Results in 2 of 6 comparisons; a rank needs 3.Not ranked. Results in 1 of 4 comparisons; a rank needs 2.Not ranked. Results in 1 of 5 comparisons; a rank needs 3.
ZMLNot ranked. Results in 4 of 22 comparisons; a rank needs 11.Not measured on this device.Not measured on this device.Not measured on this device.

Performance

Performance scope: Mobile · iOS.

LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · 4-bit · Archive 256 input / 128 output · iOS 27

Speed

Prompt processing, tok/s

Prompt processing, tok/s. Medians, tok/s.
EngineMedian Range
llama.cpp259.7 257.9 to 260.4
uzu257.7 257.1 to 259.1
ExecuTorch125.9 107.9 to 128.6
  1. Rank 1: llama.cpp 259.7 tok/s, range 257.9 to 260.4; open the experiment and its raw trials
  2. Rank 2: uzu 257.7 tok/s, range 257.1 to 259.1; open the experiment and its raw trials
  3. Rank 3: ExecuTorch 125.9 tok/s, range 107.9 to 128.6; open the experiment and its raw trials

Performance Breakdowns

Generation by precision on LFM2.5 1.2B Instruct

Generation by precision on LFM2.5 1.2B Instruct. Medians, tok/s.
Engine8-bit4-bit
uzu25.7 45.4
ExecuTorchNot measured 42.5
llama.cpp24.1 37.6

Explore Benchmarks

Open the explorer