Rankings

Explore benchmarks

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

Top Engines

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

† Rapid-MLX: 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.

† 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.cpp83 out of 100, in 1 of 1 comparisonsNo rival yet No other engine has a result in the same comparison yet.Failed Failed in 1 comparison. No trial was valid.No rival yet No other engine has a result in the same comparison yet.
Magnitude96 out of 100, in 1 of 1 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM99 out of 100, in 1 of 1 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama88 out of 100, in 1 of 1 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX100 out of 100, in 1 of 1 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ZML49 out of 100, in 1 of 1 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 2048 input / 128 output · macOS 27
RankEngineDecode and TTFT
1Rapid-MLX, approximate comparison, see details Rapid-MLX contributors532.2 tok/s 46.9 ms TTFT
2MLX LM, approximate comparison, see details Apple (ml-explore)526.9 tok/s 38.7 ms TTFT
3Magnitude, approximate comparison, see details Magnitude510.1 tok/s 48.9 ms TTFT
4Ollama, approximate comparison, see details Ollama469.0 tok/s 63.4 ms TTFT
5llama.cpp, approximate comparison, see details ggml-org442.7 tok/s 66.2 ms TTFT
6ZML, approximate comparison, see details ZML261.0 tok/s 59.6 ms TTFT
details

LFM2.5 350M on M5 Max · 64 GiB · bf16 · Archive 2048 input / 128 output · macOS 27

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

Rapid-MLX: † 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.

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 2048 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.
ComparisonRapid-MLXMLX LMMagnitudeOllamallama.cppZML
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 2048 input / 128 output · macOS 27 100, approximate99, approximate96, approximate88, approximate83, approximate49, approximate

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