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, Desktop, Speed score.
#EngineSpeed score out of 100
198 /100 Score
294 /100 Score
Not ranked in this view
Not rankedMLX LM Apple (ml-explore) Too few results
Not rankedRapid-MLX Rapid-MLX contributors Too few results
Not rankedLiteRT-LM Google AI Edge No rival yet
Not rankedMagnitude Magnitude Unsupported
Not rankeduzu Mirai Unsupported
Not rankedZML ZML Unsupported
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: litert-lm default, f16, model-dtype. The experiments here use different 8-bit schemes: litert-int8, Q8_0, mlx-affine-8bit-g64.

† llama.cpp: approximate comparison. 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.

MLX LM: Results in 1 of 2 comparisons; a rank needs 2.

Rapid-MLX: Results in 1 of 2 comparisons; a rank needs 2.

LiteRT-LM: No other engine has a result in the same comparison yet.

Magnitude: Unsupported in 3 comparisons. Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

uzu: Unsupported in 2 comparisons. uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

ZML: Unsupported in 1 comparison. zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).

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.cpp94 out of 100, in 2 of 2 comparisonsNo rival yet No other engine has a result in the same comparison yet.Not counted Partial: 5 of 6 planned trials were valid.Unsupported Unsupported in 1 comparison. Its output check failed: 7/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end.
Ollama98 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
LiteRT-LMNo 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.Not measured on this device.
uzuUnsupported Unsupported in 2 comparisons. uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).Not measured on this device.Not measured on this device.Unsupported Unsupported in 2 comparisons. uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).
MagnitudeUnsupported Unsupported in 3 comparisons. Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).Not measured on this device.Not measured on this device.Not measured on this device.
MLX LMNot ranked. Results in 1 of 2 comparisons; a rank needs 2.Not measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLXNot ranked. Results in 1 of 2 comparisons; a rank needs 2.Not measured on this device.Not measured on this device.Not measured on this device.
ZMLUnsupported Unsupported in 1 comparison. zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).Not measured on this device.Not measured on this device.Not measured on this device.

Speed

Speed, LFM2.5 2.6B on M5 Max · 64 GiB, 8-bit · Archive 256 input / 128 output · macOS 27
RankEnginePrefill
1Ollama, approximate comparison, see details Ollama4,995 tok/s
2MLX LM, approximate comparison, see details Apple (ml-explore)4,868 tok/s
3Rapid-MLX, approximate comparison, see details Rapid-MLX contributors4,220 tok/s
4llama.cpp, approximate comparison, see details ggml-org4,126 tok/s
Not rankedLiteRT-LM Google AI EdgeNot counted
Not rankedMagnitude MagnitudeUnsupported
Not rankeduzu MiraiUnsupported
details

LFM2.5 2.6B on M5 Max · 64 GiB · 8-bit · Archive 256 input / 128 output · macOS 27

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

Ollama: † Approximate comparison. 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.

MLX LM: † Approximate comparison. 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.

Rapid-MLX: † Approximate comparison. 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.

llama.cpp: † Approximate comparison. 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.

LiteRT-LM: Its output check failed: 7/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end. † Approximate comparison. 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.

Magnitude: Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

uzu: uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

Memory usage by engine

Memory usage by engine, LFM2.5 2.6B on M5 Max · 64 GiB, 8-bit · Archive 256 input / 128 output · macOS 27
RankEngineMemory
1Ollama, approximate comparison, see details Ollama2.96 GiB
2llama.cpp, approximate comparison, see details ggml-org2.96 GiB
3MLX LM, approximate comparison, see details Apple (ml-explore)3.02 GiB
4Rapid-MLX, approximate comparison, see details Rapid-MLX contributors3.28 GiB
Not rankedLiteRT-LM Google AI EdgeNot counted
Not rankedMagnitude MagnitudeUnsupported
Not rankeduzu MiraiUnsupported
details

LFM2.5 2.6B on M5 Max · 64 GiB · 8-bit · 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: litert-lm default, f16, model-dtype. The experiments here use different 8-bit schemes: litert-int8, Q8_0, mlx-affine-8bit-g64.

llama.cpp: † Approximate comparison. 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.

MLX LM: † Approximate comparison. 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.

Rapid-MLX: † Approximate comparison. 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.

LiteRT-LM: Its output check failed: 7/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end. † Approximate comparison. 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.

Magnitude: Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

uzu: uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonOllamallama.cppMLX LMRapid-MLXLiteRT-LMMagnitudeuzuZML
LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 95, approximate91, approximate100, approximate100, approximateNot countedUnsupportedUnsupportedNot run
LFM2.5 2.6B on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 10096Not runNot runNot runUnsupportedNot runUnsupported
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 countedNot countedMeasured, approximateUnsupportedUnsupportedNot run

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