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, Overall, Speed score.
#EngineSpeed score out of 100
1100 /100 Score
295 /100 Score
387 /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.

† ExecuTorch: approximate comparison. 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.

† llama.cpp: approximate comparison. 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.

† LiteRT-LM: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

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.cpp88 out of 100, in 8 of 8 comparisons95 out of 100, in 4 of 4 comparisons82 out of 100, in 2 of 2 comparisons88 out of 100, in 2 of 2 comparisons
uzu100 out of 100, in 4 of 8 comparisonsNot measured on this device.Not measured on this device.100 out of 100, in 2 of 2 comparisons
ExecuTorchNot ranked. Results in 2 of 8 comparisons; a rank needs 4.100 out of 100, in 2 of 4 comparisonsNot ranked. Results in 1 of 2 comparisons; a rank needs 2.Not ranked. Results in 1 of 2 comparisons; a rank needs 2.
LiteRT-LMNot ranked. Results in 2 of 8 comparisons; a rank needs 4.87 out of 100, in 2 of 4 comparisonsNot ranked. Results in 1 of 2 comparisons; a rank needs 2.Not measured on this device.
Magnitude91 out of 100, in 6 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
MLX LM98 out of 100, in 6 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Ollama90 out of 100, in 6 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
Rapid-MLX96 out of 100, in 4 of 8 comparisonsNot measured on this device.Not measured on this device.Not measured on this device.
ZMLNot ranked. Results in 2 of 8 comparisons; a rank needs 4.Not measured on this device.Not measured on this device.Not measured on this device.

Speed

Speed, LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB, 4-bit · Archive 256 input / 128 output · Android 16
RankEngineDecode and TTFT
1ExecuTorch, approximate comparison, see details PyTorch (Meta)76.3 tok/s TTFT not measured
2llama.cpp, approximate comparison, see details ggml-org63.5 tok/s 744 ms TTFT
Not rankedLiteRT-LM Google AI EdgeNot counted
details

LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB · 4-bit · Archive 256 input / 128 output · Android 16

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

ExecuTorch: † Approximate comparison. 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.

llama.cpp: † Approximate comparison. 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.

LiteRT-LM: 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. † Approximate comparison. 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.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB, 4-bit · Archive 256 input / 128 output · Android 16
RankEngineMemory
Not rankedExecuTorch PyTorch (Meta)Not measured
Not rankedLiteRT-LM Google AI EdgeNot counted
Not rankedllama.cpp ggml-orgNot measured
details

LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB · 4-bit · Archive 256 input / 128 output · Android 16

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, litert-lm default, f16. The experiments here use different 4-bit schemes: 8da4w, litert-int4, Q4_K_M.

LiteRT-LM: 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. † Approximate comparison. 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.

llama.cpp: No peak memory measured. † Approximate comparison. 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.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonExecuTorchllama.cppLiteRT-LM
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 100, approximate99, approximateNot counted
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 100, approximate83, approximateNot counted
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 Not run100, approximate87, approximate
LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 Not run100, approximate86, approximate
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 runFailedNot 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 runMeasuredNot run

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