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, Mobile, Speed score.
#EngineSpeed score out of 100
198 /100 Score
285 /100 Score
Not ranked in this view
Not rankeduzu Mirai Too few results
Not rankedLiteRT-LM Google AI Edge Not counted
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.

† ExecuTorch: approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m. The experiments use different effective KV cache precision: fp32, litert-lm default, f16. The experiments here use different 4-bit schemes: 8da4w, litert-int4, Q4_K_M.

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m. The experiments use different effective KV cache precision: fp32, litert-lm default, f16. The experiments here use different 4-bit schemes: 8da4w, litert-int4, Q4_K_M.

uzu: Results in 1 of 4 comparisons; a rank needs 2.

LiteRT-LM: Its output check failed: 9/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.

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
ExecuTorch87 out of 100, in 2 of 2 comparisons100 out of 100, in 2 of 2 comparisons100 out of 100, in 1 of 1 comparisons94 out of 100, in 1 of 1 comparisons
llama.cpp82 out of 100, in 2 of 2 comparisons91 out of 100, in 2 of 2 comparisons78 out of 100, in 1 of 1 comparisons83 out of 100, in 1 of 1 comparisons
uzu100 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.100 out of 100, in 1 of 1 comparisons
Magnitude84 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama84 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
LiteRT-LMNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not counted Its output check failed: 9/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not counted Its output check failed: 9/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not measured on this device.
MLX LMNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLXNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not measured on this device.Not measured on this device.Not measured on this device.

Speed

TTFT ms

Generation tok/s

Speed, LFM2.5 1.2B Instruct on iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineDecode and TTFT
1uzu, approximate comparison, see details Mirai45.4 tok/s 1,073 ms TTFT
2ExecuTorch, approximate comparison, see details PyTorch (Meta)42.5 tok/s 2,033 ms TTFT
3llama.cpp, approximate comparison, see details ggml-org37.6 tok/s 987 ms TTFT
details

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

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

uzu: † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

ExecuTorch: † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineMemory
Not rankedExecuTorch PyTorch (Meta)Not measured
Not rankedllama.cpp ggml-orgNot measured
Not rankeduzu MiraiNot measured
details

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

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

ExecuTorch: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

llama.cpp: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

uzu: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonExecuTorchllama.cppuzuLiteRT-LM
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 94, approximate83, approximate100, approximateNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 100, approximate99, approximateNot runNot counted
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 100, approximate83, approximateNot runNot counted
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 100, approximate78, approximateNot runNot counted
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot countedMeasured, approximateNot countedNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot countedNot countedNot runNot counted

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