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
188 /100 Score
283 /100 Score
Not ranked in this view
Not rankedMLX LM Apple (ml-explore) 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 rankedRapid-MLX Rapid-MLX contributors Too few results
Not rankedExecuTorch PyTorch (Meta) 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.

† Ollama: approximate comparison. 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: litert-lm default, f16, model-dtype. The experiments here use different 8-bit schemes: litert-int8, Q8_0, mlx-affine-8bit-g64. The experiments use different effective KV cache precision: f16, model-dtype.

† 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: litert-lm default, f16, model-dtype. The experiments here use different 8-bit schemes: litert-int8, Q8_0, mlx-affine-8bit-g64. The experiments use different effective KV cache precision: f16, model-dtype. 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.

MLX LM: Results in 9 of 21 comparisons; a rank needs 11.

uzu: Results in 8 of 21 comparisons; a rank needs 11.

LiteRT-LM: Results in 6 of 21 comparisons; a rank needs 11.

Magnitude: Results in 6 of 21 comparisons; a rank needs 11.

Rapid-MLX: Results in 6 of 21 comparisons; a rank needs 11.

ExecuTorch: Results in 4 of 21 comparisons; a rank needs 11.

ZML: Results in 2 of 21 comparisons; a rank needs 11.

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.cpp84 out of 100, in 11 of 11 comparisons94 out of 100, in 3 of 3 comparisons88 out of 100, in 3 of 3 comparisons69 out of 100, in 4 of 4 comparisons
LiteRT-LMNot ranked. Results in 2 of 11 comparisons; a rank needs 6.74 out of 100, in 2 of 3 comparisons96 out of 100, in 2 of 3 comparisonsNot measured on this device.
uzuNot ranked. Results in 4 of 11 comparisons; a rank needs 6.Not measured on this device.Not measured on this device.100 out of 100, in 4 of 4 comparisons
Magnitude89 out of 100, in 6 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM99 out of 100, in 9 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama88 out of 100, in 11 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX99 out of 100, in 6 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ExecuTorchNot ranked. Results in 1 of 11 comparisons; a rank needs 6.Not ranked. Results in 1 of 3 comparisons; a rank needs 2.Not ranked. Results in 1 of 3 comparisons; a rank needs 2.Not ranked. Results in 1 of 4 comparisons; a rank needs 2.
ZMLNot ranked. Results in 2 of 11 comparisons; a rank needs 6.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.
ComparisonOllamallama.cppMLX LMuzuLiteRT-LMMagnitudeRapid-MLXExecuTorchZML
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not run83, approximateNot run100, approximateNot runNot runNot run94, approximateNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not run94, approximateNot run100, approximateNot runNot runNot runNot runNot run
LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not run43, approximateNot run100, approximateNot runNot runNot runNot countedNot run
LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not run67, approximateNot run100, approximateNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 84, approximate81, approximateNot counted100, approximateNot counted82, approximateNot counted87, approximateNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 87, approximate87, approximate96, approximate100, approximate32, approximate88, approximate97, approximateNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 100, approximate95, approximate100, approximateNot runNot run100, approximate99, approximateNot run96, approximate
LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 95, approximate91, approximate100, approximateUnsupportedNot countedUnsupported100, approximateNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 10096Not runNot runNot runUnsupportedNot runNot runUnsupported
LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 67, approximate62, approximate100, approximate90, approximateNot counted82, approximate100, approximateNot countedNot run
LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 77, approximate75, approximate100, approximate97, approximate24, approximate93, approximate98, approximateNot runNot run
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 84, approximate81, approximate100, approximateNot runNot run92, approximate98, approximateNot run73, approximate
Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 78, approximate75, approximate100, approximateUnsupportedNot runUnsupportedNot runNot runNot run
Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 100, approximate98, approximate97, approximateUnsupportedNot runUnsupportedNot runNot runNot run
Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 256 input / 128 output · macOS 27 100, approximate95, approximate100, approximateNot runNot runUnsupportedNot runNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not run83, approximateNot runNot runNot countedNot runNot run100, approximateNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run100, approximateNot runNot run86, approximateNot runNot runNot runNot run
LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run100, approximateNot runNot run64, approximateNot runNot runNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not run78, approximateNot runNot runNot countedNot runNot run100, approximateNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run87, approximateNot runNot run100, approximateNot runNot runNot runNot run
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run100, approximateNot runNot run93, approximateNot 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 enginesNot runUnsupportedNot runNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot countedNot runUnsupportedNot runNot runNot runNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runUnsupportedNot runUnsupportedNot runNot runNot runNot runNot run
LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runMeasuredNot runNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 Not counted: fewer than two scored enginesNot countedNot countedNot countedUnsupportedMeasured, approximateUnsupportedNot countedNot 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 enginesNot runMeasuredNot runNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot countedNot runNot runMeasured, approximateNot runNot runNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runMeasured, approximateNot runNot runNot countedNot runNot runNot runNot 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 runMeasured, approximateNot runNot runNot countedNot runNot runNot countedNot run
LFM2.5 350M on OnePlus 13 · 16 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runMeasuredNot 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 enginesNot runFailedNot runNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot countedNot runNot runMeasured, approximateNot runNot runNot runNot run
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 runNot countedNot runNot runNot countedNot runNot runNot runNot 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 runMeasured, approximateNot runNot runNot countedNot runNot runNot countedNot run
LFM2.5 350M on Pixel 8 · 8 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runMeasuredNot 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