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
1100 /100 Score
287 /100 Score
384 /100 Score
484 /100 Score
582 /100 Score
Not ranked in this view
Not rankedLiteRT-LM Google AI Edge Not counted
Not rankedMLX LM Apple (ml-explore) Not counted
Not rankedRapid-MLX Rapid-MLX contributors Not counted
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.

† uzu: approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mirai-m, where most use Q4_K_M.

† ExecuTorch: approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-4w-g64, where most use Q4_K_M.

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

† Magnitude: approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

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

LiteRT-LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.

MLX LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.

Rapid-MLX: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.

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
ExecuTorch87 out of 100, in 2 of 2 comparisons100 out of 100, in 2 of 2 comparisons100 out of 100, in 1 of 1 comparisons94 out of 100, in 1 of 1 comparisons
llama.cpp82 out of 100, in 2 of 2 comparisons91 out of 100, in 2 of 2 comparisons78 out of 100, in 1 of 1 comparisons83 out of 100, in 1 of 1 comparisons
uzu100 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.100 out of 100, in 1 of 1 comparisons
Magnitude84 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama84 out of 100, in 2 of 2 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
LiteRT-LMNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not counted Its output check failed: 9/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not counted Its output check failed: 9/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not measured on this device.
MLX LMNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.Not measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLXNot counted Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.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 M5 Max · 64 GiB, 4-bit · Archive 256 input / 128 output · macOS 27
RankEngineDecode and TTFT
1uzu, approximate comparison, see details Mirai540.7 tok/s 75.2 ms TTFT
2ExecuTorch, approximate comparison, see details PyTorch (Meta)472.1 tok/s 52.3 ms TTFT
3Ollama, approximate comparison, see details Ollama454.6 tok/s 30.6 ms TTFT
4Magnitude, approximate comparison, see details Magnitude444.5 tok/s 26.6 ms TTFT
5llama.cpp, approximate comparison, see details ggml-org438.1 tok/s 34.2 ms TTFT
Not rankedLiteRT-LM Google AI EdgeNot counted
Not rankedMLX LM Apple (ml-explore)Not counted
Not rankedRapid-MLX Rapid-MLX contributorsNot counted
details

LFM2.5 1.2B Instruct on M5 Max · 64 GiB · 4-bit · Archive 256 input / 128 output · macOS 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mirai-m, where most use Q4_K_M.

ExecuTorch: † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-4w-g64, where most use Q4_K_M.

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

Magnitude: † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

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

LiteRT-LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: litert-int4, where most use Q4_K_M.

MLX LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-affine-4bit-g64, where most use Q4_K_M.

Rapid-MLX: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-affine-4bit-g64, where most use Q4_K_M.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on M5 Max · 64 GiB, 4-bit · Archive 256 input / 128 output · macOS 27
RankEngineMemory
1uzu, approximate comparison, see details Mirai0.90 GiB
2Ollama, approximate comparison, see details Ollama0.93 GiB
3llama.cpp, approximate comparison, see details ggml-org0.93 GiB
4Magnitude, approximate comparison, see details Magnitude1.56 GiB
Not rankedExecuTorch PyTorch (Meta)Not measured
Not rankedLiteRT-LM Google AI EdgeNot counted
Not rankedMLX LM Apple (ml-explore)Not counted
Not rankedRapid-MLX Rapid-MLX contributorsNot counted
details

LFM2.5 1.2B Instruct on M5 Max · 64 GiB · 4-bit · Archive 256 input / 128 output · macOS 27

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

uzu: † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mirai-m, where most use Q4_K_M.

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

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

Magnitude: † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its phases were timed by the harness clock around the engine API, so they include transport that engine counters leave out.

ExecuTorch: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-4w-g64, where most use Q4_K_M.

LiteRT-LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: litert-int4, where most use Q4_K_M.

MLX LM: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-affine-4bit-g64, where most use Q4_K_M.

Rapid-MLX: Its output check failed: 10/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none. † Approximate comparison. The experiments use different effective KV cache precision: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. Its weights are 4-bit in another scheme: mlx-affine-4bit-g64, where most use Q4_K_M.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonuzuExecuTorchOllamaMagnitudellama.cppLiteRT-LMMLX LMRapid-MLX
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 100, approximate86, approximate84, approximate85, approximate83, approximateNot countedNot countedNot counted
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 100, approximate87, approximate84, approximate82, approximate81, approximateNot countedNot countedNot counted
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · 2048 input / 128 output · macOS 27 Not counted: fewer than two scored enginesNot runNot runNot runNot runNot countedNot runNot countedNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · 256 input / 128 output · macOS 27 Not counted: fewer than two scored enginesNot runNot runNot runNot runMeasured, approximateNot runNot countedNot run

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