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
197 /100 Score
289 /100 Score
386 /100 Score
Not ranked in this view
Not rankedMagnitude Magnitude Too few results
Not rankedRapid-MLX Rapid-MLX contributors Too few results
Not rankedLiteRT-LM Google AI Edge Too few results
Not rankeduzu Mirai 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.

† MLX LM: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 8-bit in another scheme: mlx-affine-8bit-g64, where most use Q8_0. 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype. Its weights are 4-bit in another scheme: mlx-affine-4bit-g64, where most use Q4_K_M. The experiments use different effective KV cache precision: f16, model-dtype. Its weights are 2-bit in another scheme: mlx-affine-2bit-g128, where most use Q2_0.

† 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype. The experiments use different effective KV cache precision: f16, model-dtype.

† llama.cpp: approximate comparison. 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype. 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.

Magnitude: Results in 6 of 16 comparisons; a rank needs 8.

Rapid-MLX: Results in 6 of 16 comparisons; a rank needs 8.

LiteRT-LM: Results in 5 of 16 comparisons; a rank needs 8.

uzu: Results in 4 of 16 comparisons; a rank needs 8.

ExecuTorch: Results in 2 of 16 comparisons; a rank needs 8.

ZML: Results in 2 of 16 comparisons; a rank needs 8.

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.cpp85 out of 100, in 11 of 11 comparisons100 out of 100, in 3 of 3 comparisons81 out of 100, in 1 of 1 comparisons69 out of 100, in 1 of 1 comparisons
LiteRT-LMNot ranked. Results in 2 of 11 comparisons; a rank needs 6.81 out of 100, in 2 of 3 comparisons100 out of 100, in 1 of 1 comparisonsNot measured on this device.
uzuNot ranked. Results in 3 of 11 comparisons; a rank needs 6.Not measured on this device.Not measured on this device.100 out of 100, in 1 of 1 comparisons
Magnitude93 out of 100, in 6 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM97 out of 100, in 9 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama89 out of 100, in 11 of 11 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX97 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 counted Partial: 2 of 6 planned trials were valid.Not counted Partial: 4 of 6 planned trials were valid.
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

Speed, LFM2.5 350M on iPhone 12 · 4 GB, 8-bit · Archive 2048 input / 128 output · iOS 27
RankEnginePrefill
1llama.cpp, approximate comparison, see details ggml-org927.4 tok/s
2uzu, approximate comparison, see details Mirai895.5 tok/s
details

LFM2.5 350M on iPhone 12 · 4 GB · 8-bit · Archive 2048 input / 128 output · iOS 27

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

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

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

Memory usage by engine

Memory usage by engine, LFM2.5 350M on iPhone 12 · 4 GB, 8-bit · Archive 2048 input / 128 output · iOS 27
RankEngineMemory
Not rankedllama.cpp ggml-orgNot measured
Not rankeduzu MiraiNot measured
details

LFM2.5 350M on iPhone 12 · 4 GB · 8-bit · Archive 2048 input / 128 output · iOS 27

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

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

uzu: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonMLX LMOllamallama.cppMagnitudeRapid-MLXLiteRT-LMuzuExecuTorchZML
LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 2048 input / 128 output · iOS 27 Not runNot run69, approximateNot runNot runNot run100, approximateNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 Not counted84, approximate83, approximate85, approximateNot countedNot counted100, approximate86, approximateNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 92, approximate87, approximate87, approximate89, approximate92, approximate32, approximate100, approximateNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · Archive 2048 input / 128 output · macOS 27 99, approximate99, approximate92, approximate100, approximate98, approximateNot runNot runNot run76, approximate
LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 100, approximate96, approximate89, approximateUnsupported100, approximateNot countedUnsupportedNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB bf16 · Archive 2048 input / 128 output · macOS 27 Not run10097UnsupportedNot runNot runNot runNot runUnsupported
LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 95, approximate74, approximate69, approximate93, approximate100, approximateNot countedFailedNot countedNot run
LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 90, approximate77, approximate76, approximate96, approximate92, approximate26, approximate100, approximateNot runNot run
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 2048 input / 128 output · macOS 27 99, approximate88, approximate83, approximate96, approximate100, approximateNot runNot runNot run49, approximate
Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 100, approximate78, approximate76, approximateUnsupportedNot runNot runUnsupportedNot runNot run
Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 97, approximate100, approximate98, approximateUnsupportedNot runNot runUnsupportedNot runNot run
Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 2048 input / 128 output · macOS 27 97, approximate100, approximate96, approximateUnsupportedNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not runNot run99, approximateNot runNot runNot countedNot run100, approximateNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not runNot run100, approximateNot runNot run87, approximateNot runNot runNot run
LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not runNot run100, approximateNot runNot run76, approximateNot runNot runNot run
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not runNot run81, approximateNot runNot run100, approximateNot runNot runNot run
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 runNot runMeasured, approximateNot runNot runNot runNot countedNot countedNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot runNot countedNot runNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB bf16 · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runUnsupportedNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 4-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runNot runUnsupportedNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 8-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runUnsupportedNot runNot runNot runUnsupportedNot runNot run
LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot runFailedNot countedNot run
LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runMeasuredNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 Not counted: fewer than two scored enginesNot countedNot countedNot countedUnsupportedNot countedMeasured, approximateUnsupportedNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB bf16 · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runFailedNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runMeasured, approximateNot runNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot countedNot runNot runNot run
LFM2.5 350M on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot countedNot runNot countedNot run
LFM2.5 350M on OnePlus 13 · 16 GB bf16 · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasuredNot runNot runNot runNot runNot runNot 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 runNot runNot countedNot runNot runNot countedNot runNot countedNot run
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 runNot runMeasured, approximateNot runNot runNot countedNot runNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB bf16 · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runFailedNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on Pixel 8 · 8 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runFailedNot runNot runNot countedNot runNot runNot run
LFM2.5 2.6B on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runFailedNot runNot runFailedNot runNot runNot run
LFM2.5 350M on Pixel 8 · 8 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runNot countedNot runNot countedNot run
LFM2.5 350M on Pixel 8 · 8 GB bf16 · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runFailedNot 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