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
1100 /100 Score
277 /100 Score
373 /100 Score
Not ranked in this view
Not rankedExecuTorch PyTorch (Meta) 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.

† 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. The experiments use different effective KV cache precision: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.

† 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: 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: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

ExecuTorch: Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.

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.cpp72 out of 100, in 3 of 3 comparisons100 out of 100, in 1 of 1 comparisons100 out of 100, in 1 of 1 comparisons53 out of 100, in 2 of 2 comparisons
LiteRT-LMNot ranked. Results in 1 of 3 comparisons; a rank needs 2.64 out of 100, in 1 of 1 comparisons93 out of 100, in 1 of 1 comparisonsNot measured on this device.
uzu94 out of 100, in 2 of 3 comparisonsNot measured on this device.Not measured on this device.100 out of 100, in 2 of 2 comparisons
Magnitude89 out of 100, in 3 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM100 out of 100, in 3 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama76 out of 100, in 3 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX98 out of 100, in 3 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ExecuTorchNot counted Its output check failed: 6/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.Not counted Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.Not counted Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.Not counted Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.
ZMLNot ranked. Results in 1 of 3 comparisons; a rank needs 2.Not measured on this device.Not measured on this device.Not measured on this device.

Speed

TTFT ms

Generation tok/s

Speed, LFM2.5 350M on iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineDecode and TTFT
1uzu, approximate comparison, see details Mirai130.8 tok/s 384 ms TTFT
2llama.cpp, approximate comparison, see details ggml-org56.0 tok/s 314 ms TTFT
Not rankedExecuTorch PyTorch (Meta)Not counted
details

LFM2.5 350M 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.

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.

ExecuTorch: Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128. † 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 350M on iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineMemory
Not rankedExecuTorch PyTorch (Meta)Not counted
Not rankedllama.cpp ggml-orgNot measured
Not rankeduzu MiraiNot measured
details

LFM2.5 350M 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: Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128. † 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.
ComparisonuzuLiteRT-LMllama.cppExecuTorch
LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 100, approximateNot run43, approximateNot counted
LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 100, approximateNot run67, approximateNot run
LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run64, approximate100, approximateNot run
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run93, approximate100, approximateNot run
LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runMeasuredNot run
LFM2.5 350M on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot countedMeasured, approximateNot counted
LFM2.5 350M on OnePlus 13 · 16 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasuredNot run
LFM2.5 350M on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot countedMeasured, approximateNot counted
LFM2.5 350M on Pixel 8 · 8 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasuredNot run

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