Rankings

Explore benchmarks

Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.

Clear filters

Top Engines

Top Engines, Overall, Speed score.
#EngineSpeed score out of 100
198 /100 Score
289 /100 Score
details

Speed Decode speed: tokens generated per second.

Score: 100 is the best result in every comparison an engine entered; 80 is 80% of the best, on average. Only complete experiments with a passed output check count. How rankings work

The score combines counted comparisons. Select one comparison to see its measured values.

† LiteRT-LM: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

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.cpp87 out of 100, in 8 of 8 comparisons100 out of 100, in 4 of 4 comparisons89 out of 100, in 3 of 3 comparisons76 out of 100, in 3 of 3 comparisons
LiteRT-LM28 out of 100, in 4 of 8 comparisons78 out of 100, in 4 of 4 comparisons98 out of 100, in 3 of 3 comparisonsNot measured on this device.
uzu99 out of 100, in 4 of 8 comparisonsNot measured on this device.Not measured on this device.100 out of 100, in 3 of 3 comparisons
Magnitude92 out of 100, in 4 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM96 out of 100, in 8 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama89 out of 100, in 8 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX96 out of 100, in 6 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.

Speed

Speed, LFM2.5 1.2B Instruct on Pixel 8 · 8 GB, 8-bit · Archive 256 input / 128 output · Android 16
RankEngineDecode and TTFT
1LiteRT-LM, approximate comparison, see details Google AI Edge18.3 tok/s TTFT not measured
2llama.cpp, approximate comparison, see details ggml-org15.9 tok/s 1,923 ms TTFT
details

LFM2.5 1.2B Instruct on Pixel 8 · 8 GB · 8-bit · Archive 256 input / 128 output · Android 16

Medians with the model warmed; model loading is excluded. Each table uses one matched comparison.

LiteRT-LM: † Approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on Pixel 8 · 8 GB, 8-bit · Archive 256 input / 128 output · Android 16
RankEngineMemory
Not rankedLiteRT-LM Google AI EdgeNot measured
Not rankedllama.cpp ggml-orgNot measured
details

LFM2.5 1.2B Instruct on Pixel 8 · 8 GB · 8-bit · Archive 256 input / 128 output · Android 16

Memory ranks require comparable, calibrated measurements. Unavailable measurements remain unranked.

LiteRT-LM: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

llama.cpp: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonLiteRT-LMllama.cpp
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 100, approximate87, approximate
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 100, approximate81, approximate
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 93, approximate100, approximate
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot countedMeasured, approximate
LFM2.5 2.6B on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesFailedFailed
LFM2.5 2.6B on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot countedNot counted

Each engine’s Speed score in each matched comparison, out of 100, or why it has none. How rankings work