Rankings

Explore benchmarks

Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.

Top Engines

Top Engines, Desktop, Speed score.
#EngineSpeed score out of 100
199 /100 Score
299 /100 Score
394 /100 Score
486 /100 Score
582 /100 Score
660 /100 Score
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: f16, magnitude default, model-dtype, zml default.

† Rapid-MLX: approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

† Magnitude: approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

† Ollama: approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

† ZML: approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

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.cpp82 out of 100, in 2 of 2 comparisonsNo rival yet No other engine has a result in the same comparison yet.No rival yet No other engine has a result in the same comparison yet.No rival yet No other engine has a result in the same comparison yet.
Magnitude94 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM99 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama86 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX99 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ZML60 out of 100, in 2 of 2 comparisonsNot 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 M5 Max · 64 GiB, bf16 · Archive 256 input / 128 output · macOS 27
RankEngineDecode and TTFT
1MLX LM, approximate comparison, see details Apple (ml-explore)571.7 tok/s 18.1 ms TTFT
2Rapid-MLX, approximate comparison, see details Rapid-MLX contributors559.0 tok/s 26.2 ms TTFT
3Magnitude, approximate comparison, see details Magnitude524.1 tok/s 19.1 ms TTFT
4Ollama, approximate comparison, see details Ollama479.5 tok/s 22.3 ms TTFT
5llama.cpp, approximate comparison, see details ggml-org464.2 tok/s 23.4 ms TTFT
6ZML, approximate comparison, see details ZML420.2 tok/s 15.9 ms TTFT
details

LFM2.5 350M on M5 Max · 64 GiB · bf16 · Archive 256 input / 128 output · macOS 27

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

MLX LM: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

Rapid-MLX: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

Magnitude: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

Ollama: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

ZML: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

Memory usage by engine

details

LFM2.5 350M on M5 Max · 64 GiB · bf16 · Archive 256 input / 128 output · macOS 27

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

Ollama: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

MLX LM: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

Rapid-MLX: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default.

Magnitude: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

ZML: † Approximate comparison. The experiments use different effective KV cache precision: f16, magnitude default, model-dtype, zml default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonMLX LMRapid-MLXMagnitudeOllamallama.cppZML
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 2048 input / 128 output · macOS 27 99, approximate100, approximate96, approximate88, approximate83, approximate49, approximate
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 100, approximate98, approximate92, approximate84, approximate81, approximate73, approximate

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