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
187 /100 Score
Not ranked in this view
Not rankedExecuTorch PyTorch (Meta) Too few results
Not rankeduzu Mirai Too few results
Not rankedLiteRT-LM Google AI Edge Too few results
Not rankedMagnitude Magnitude Too few results
Not rankedOllama Ollama Too few results
Not rankedMLX LM Apple (ml-explore) Too few results
Not rankedRapid-MLX Rapid-MLX contributors Too few results
Not rankedZML ZML Too few results
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.

† 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. The experiments use different effective KV cache precision: litert-lm default, f16, magnitude default, model-dtype, uzu default. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. 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. 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: Results in 4 of 9 comparisons; a rank needs 5.

uzu: Results in 4 of 9 comparisons; a rank needs 5.

LiteRT-LM: Results in 3 of 9 comparisons; a rank needs 5.

Magnitude: Results in 3 of 9 comparisons; a rank needs 5.

Ollama: Results in 3 of 9 comparisons; a rank needs 5.

MLX LM: Results in 2 of 9 comparisons; a rank needs 5.

Rapid-MLX: Results in 2 of 9 comparisons; a rank needs 5.

ZML: Results in 1 of 9 comparisons; a rank needs 5.

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.cpp88 out of 100, in 3 of 3 comparisons91 out of 100, in 2 of 2 comparisons82 out of 100, in 2 of 2 comparisons88 out of 100, in 2 of 2 comparisons
uzu100 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
Magnitude90 out of 100, in 3 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM98 out of 100, in 2 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama90 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 2 of 3 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ExecuTorchNot ranked. Results in 1 of 3 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.
LiteRT-LMNot ranked. Results in 1 of 3 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.Not measured on this device.
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 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.
Comparisonllama.cppExecuTorchuzuLiteRT-LMMagnitudeOllamaMLX LMRapid-MLXZML
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 83, approximate94, approximate100, approximateNot runNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 94, approximateNot run100, approximateNot runNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 81, approximate87, approximate100, approximateNot counted82, approximate84, approximateNot countedNot countedNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 87, approximateNot run100, approximate32, approximate88, approximate87, approximate96, approximate97, approximateNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 95, approximateNot runNot runNot run100, approximate100, approximate100, approximate99, approximate96, approximate
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 83, approximate100, approximateNot runNot countedNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 100, approximateNot runNot run86, approximateNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 78, approximate100, approximateNot runNot countedNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 87, approximateNot runNot run100, approximateNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesUnsupportedNot runNot runNot runNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesMeasuredNot runNot runNot runNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesFailedNot runNot runNot runNot runNot runNot runNot runNot run

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