Rankings

Explore benchmarks

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

Top Engines

Top Engines, Overall, Speed score.
#EngineSpeed score out of 100
198 /100 Score
288 /100 Score
385 /100 Score
Not ranked in this view
Not rankedMagnitude Magnitude Too few results
Not rankedRapid-MLX Rapid-MLX contributors Too few results
Not rankeduzu Mirai Too few results
Not rankedLiteRT-LM Google AI Edge 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: f16, model-dtype. 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. 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: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m. 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: f16, model-dtype. 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: 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 12 of 39 comparisons; a rank needs 20.

Rapid-MLX: Results in 12 of 39 comparisons; a rank needs 20.

uzu: Results in 12 of 39 comparisons; a rank needs 20.

LiteRT-LM: Results in 11 of 39 comparisons; a rank needs 20.

ExecuTorch: Results in 6 of 39 comparisons; a rank needs 20.

ZML: Results in 4 of 39 comparisons; a rank needs 20.

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 24 of 24 comparisons97 out of 100, in 6 of 6 comparisons86 out of 100, in 4 of 4 comparisons69 out of 100, in 5 of 5 comparisons
LiteRT-LMNot ranked. Results in 4 of 24 comparisons; a rank needs 12.78 out of 100, in 4 of 6 comparisons98 out of 100, in 3 of 4 comparisonsNot measured on this device.
uzuNot ranked. Results in 7 of 24 comparisons; a rank needs 12.Not measured on this device.Not measured on this device.100 out of 100, in 5 of 5 comparisons
Magnitude91 out of 100, in 12 of 24 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM98 out of 100, in 20 of 24 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama88 out of 100, in 22 of 24 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX98 out of 100, in 12 of 24 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ExecuTorchNot ranked. Results in 2 of 24 comparisons; a rank needs 12.Not ranked. Results in 2 of 6 comparisons; a rank needs 3.Not ranked. Results in 1 of 4 comparisons; a rank needs 2.Not ranked. Results in 1 of 5 comparisons; a rank needs 3.
ZMLNot ranked. Results in 4 of 24 comparisons; a rank needs 12.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 iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineDecode and TTFT
1uzu, approximate comparison, see details Mirai45.4 tok/s 1,073 ms TTFT
2ExecuTorch, approximate comparison, see details PyTorch (Meta)42.5 tok/s 2,033 ms TTFT
3llama.cpp, approximate comparison, see details ggml-org37.6 tok/s 987 ms TTFT
details

LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · 4-bit · Archive 256 input / 128 output · iOS 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: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

ExecuTorch: † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on iPhone 12 · 4 GB, 4-bit · Archive 256 input / 128 output · iOS 27
RankEngineMemory
Not rankedExecuTorch PyTorch (Meta)Not measured
Not rankedllama.cpp ggml-orgNot measured
Not rankeduzu MiraiNot measured
details

LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · 4-bit · Archive 256 input / 128 output · iOS 27

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

ExecuTorch: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

llama.cpp: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

uzu: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: fp32, f16, uzu default. The experiments here use different 4-bit schemes: 8da4w, Q4_K_M, mirai-m.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonMLX LMOllamallama.cppMagnitudeRapid-MLXuzuLiteRT-LMExecuTorchZML
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not runNot run83, approximateNot runNot run100, approximateNot run94, approximateNot run
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not runNot run94, approximateNot runNot run100, approximateNot runNot runNot run
LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not runNot run43, approximateNot runNot run100, approximateNot runNot countedNot run
LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 2048 input / 128 output · iOS 27 Not runNot run69, approximateNot runNot run100, approximateNot runNot runNot run
LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not runNot run67, approximateNot runNot run100, approximateNot runNot 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 counted100, approximateNot counted86, approximateNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 Not counted84, approximate81, approximate82, approximateNot counted100, approximateNot counted87, 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, approximate100, approximate32, approximateNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 96, approximate87, approximate87, approximate88, approximate97, approximate100, approximate32, 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 1.2B Instruct on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 100, approximate100, approximate95, approximate100, approximate99, approximateNot runNot runNot run96, approximate
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · 2048 input / 128 output · macOS 27 100, approximateNot run92, approximateNot runNot runNot runNot runNot runNot run
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · 256 input / 128 output · macOS 27 100, approximateNot run85, approximateNot runNot runNot runNot runNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 100, approximate96, approximate89, approximateUnsupported100, approximateUnsupportedNot countedNot runNot run
LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 100, approximate95, approximate91, approximateUnsupported100, approximateUnsupportedNot countedNot 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 2.6B on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 Not run10096UnsupportedNot 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, approximateFailedNot countedNot countedNot run
LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 100, approximate67, approximate62, approximate82, approximate100, approximate90, approximateNot countedNot countedNot run
LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 90, approximate77, approximate76, approximate96, approximate92, approximate100, approximate26, approximateNot runNot run
LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 100, approximate77, approximate75, approximate93, approximate98, approximate97, approximate24, 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
LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 100, approximate84, approximate81, approximate92, approximate98, approximateNot runNot runNot run73, approximate
Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 100, approximate78, approximate76, approximateUnsupportedNot runUnsupportedNot runNot runNot run
Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 100, approximate78, approximate75, approximateUnsupportedNot runUnsupportedNot runNot runNot run
Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 97, approximate100, approximate98, approximateUnsupportedNot runUnsupportedNot runNot runNot run
Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 97, approximate100, approximate98, approximateUnsupportedNot runUnsupportedNot runNot 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
Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 256 input / 128 output · macOS 27 100, approximate100, approximate95, 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 runNot counted100, approximateNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not runNot run83, approximateNot runNot runNot runNot counted100, 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 runNot run87, approximateNot runNot run
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not runNot run100, approximateNot runNot runNot run86, approximateNot runNot run
LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not runNot run100, approximateNot runNot runNot run76, approximateNot runNot run
LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not runNot run100, approximateNot runNot runNot run64, approximateNot runNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not runNot run78, approximateNot runNot runNot runNot counted100, approximateNot run
LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not runNot run87, approximateNot runNot runNot run100, approximateNot runNot run
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not runNot run81, approximateNot runNot runNot run100, approximateNot runNot run
LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not runNot run100, approximateNot runNot runNot run93, approximateNot 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 countedNot runNot 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 countedNot runNot 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 1.2B Instruct on iPhone 12 · 4 GB bf16 · Archive 256 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 runUnsupportedNot runNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runUnsupportedNot runNot 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 runUnsupportedNot runNot runNot run
LFM2.5 2.6B on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runUnsupportedNot runNot runUnsupportedNot runNot 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 runFailedNot runNot 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 350M on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored enginesNot runNot runMeasuredNot runNot runNot runNot runNot runNot run
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 countedNot runNot countedNot runNot runNot runNot runNot runNot 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 countedNot runMeasured, approximateNot 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 countedUnsupportedMeasured, approximateNot runNot run
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 countedUnsupportedNot countedUnsupportedMeasured, approximateNot 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 1.2B Instruct on OnePlus 13 · 16 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasuredNot 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 runNot runMeasured, approximateNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runNot runMeasured, approximateNot 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 runNot countedNot runNot run
LFM2.5 2.6B on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot runNot countedNot 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 runNot countedNot countedNot run
LFM2.5 350M on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot runNot countedNot 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 350M on OnePlus 13 · 16 GB bf16 · Archive 256 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 runNot countedNot 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 runNot countedNot 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 1.2B Instruct on Pixel 8 · 8 GB bf16 · Archive 256 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 runNot countedNot runNot run
LFM2.5 2.6B on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runNot runMeasured, approximateNot 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 runNot runFailedNot runNot run
LFM2.5 2.6B on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runNot countedNot runNot runNot runNot countedNot 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 runNot countedNot countedNot run
LFM2.5 350M on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasured, approximateNot runNot runNot runNot countedNot 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
LFM2.5 350M on Pixel 8 · 8 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored enginesNot runNot runMeasuredNot 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