Explore benchmarks
Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.
Top Engines
| # | Engine | Speed score out of 100 |
|---|---|---|
| 1 | ExecuTorch†, an approximate comparison, see details | 94 /100 Score |
| ||
| 2 | Ollama†, an approximate comparison, see details | 77 /100 Score |
| ||
| 3 | llama.cpp†, an approximate comparison, see details | 74 /100 Score |
| ||
| Not ranked in this view | ||
| Not ranked | uzu | Too few results |
| Not ranked | Magnitude | Too few results |
| Not ranked | MLX LM | Too few results |
| Not ranked | Rapid-MLX | Too few results |
| Not ranked | LiteRT-LM | No rival yet |
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, 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: 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. 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.
† 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: 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: bf16, fp32, litert-lm default, f16, magnitude default, model-dtype, uzu default. 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. 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.
uzu: Results in 5 of 11 comparisons; a rank needs 6.
Magnitude: Results in 4 of 11 comparisons; a rank needs 6.
MLX LM: Results in 4 of 11 comparisons; a rank needs 6.
Rapid-MLX: Results in 2 of 11 comparisons; a rank needs 6.
LiteRT-LM: No other engine has a result in the same comparison yet.
Coverage
| Desktop | Mobile | |||
|---|---|---|---|---|
| M5 Max 64 GiB macOS 27 Apple M5 Max | OnePlus 13 16 GB Android 16 Qualcomm Snapdragon 8 Elite (SM8750) | Pixel 8 8 GB Android 16 Google Tensor G3 | iPhone 12 4 GB iOS 27 Apple A14 Bionic | |
| llama.cpp | 746/6 out of 100, in 6 of 6 comparisons | 912/2 out of 100, in 2 of 2 comparisons | 781/1 out of 100, in 1 of 1 comparisons | 602/2 out of 100, in 2 of 2 comparisons |
| ExecuTorch | 2/6Not ranked. Results in 2 of 6 comparisons; a rank needs 3. | 1002/2 out of 100, in 2 of 2 comparisons | 1001/1 out of 100, in 1 of 1 comparisons | 1/2Not ranked. Results in 1 of 2 comparisons; a rank needs 2. |
| uzu | 973/6 out of 100, in 3 of 6 comparisons | Not measured on this device. | Not measured on this device. | 1002/2 out of 100, in 2 of 2 comparisons |
| Magnitude | 864/6 out of 100, in 4 of 6 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| MLX LM | 994/6 out of 100, in 4 of 6 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Ollama | 776/6 out of 100, in 6 of 6 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| LiteRT-LM | 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. | No rival yet No other engine has a result in the same comparison yet. | Not measured on this device. |
| Rapid-MLX | 2/6Not ranked. Results in 2 of 6 comparisons; a rank needs 3. | Not measured on this device. | Not measured on this device. | Not measured on this device. |
Speed
| Rank | Engine | Decode and TTFT |
|---|---|---|
| 1 | uzu†, approximate comparison, see details | 45.4 tok/s 1,073 ms TTFT |
| 2 | ExecuTorch†, approximate comparison, see details | 42.5 tok/s 2,033 ms TTFT |
| 3 | llama.cpp†, approximate comparison, see details | 37.6 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
| Rank | Engine | Memory |
|---|---|---|
| Not ranked | ExecuTorch | Not measured |
| Not ranked | llama.cpp | Not measured |
| Not ranked | uzu | Not 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
| Comparison | ExecuTorch | Ollama | llama.cpp | uzu | Magnitude | MLX LM | Rapid-MLX | LiteRT-LM |
|---|---|---|---|---|---|---|---|---|
| LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 | 94†, approximate | Not run | 83†, approximate | 100†, approximate | Not run | Not run | Not run | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 | Not counted | Not run | 43†, approximate | 100†, approximate | Not run | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 | 86†, approximate | 84†, approximate | 83†, approximate | 100†, approximate | 85†, approximate | Not counted | Not counted | Not counted |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | 87†, approximate | 84†, approximate | 81†, approximate | 100†, approximate | 82†, approximate | Not counted | Not counted | Not counted |
| LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 | Not counted | 74†, approximate | 69†, approximate | Failed | 93†, approximate | 95†, approximate | 100†, approximate | Not counted |
| LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | Not counted | 67†, approximate | 62†, approximate | 90†, approximate | 82†, approximate | 100†, approximate | 100†, approximate | Not counted |
| Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 2048 input / 128 output · macOS 27 | Not run | 78†, approximate | 76†, approximate | Unsupported | Unsupported | 100†, approximate | Not run | Not run |
| Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | Not run | 78†, approximate | 75†, approximate | Unsupported | Unsupported | 100†, approximate | Not run | Not run |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 | 100†, approximate | Not run | 99†, approximate | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 | 100†, approximate | Not run | 83†, approximate | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 | 100†, approximate | Not run | 78†, approximate | Not run | Not run | Not run | Not run | Not counted |
| 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 engines | Not counted | Not run | Measured†, approximate | Not counted | Not run | Not run | Not run | Not 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 engines | Not run | Not run | Not counted | Unsupported | Not run | Not run | Not run | Not 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 engines | Not run | Not run | Not counted | Unsupported | Not run | Not run | Not run | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB 4-bit · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored engines | Not counted | Not run | Measured†, approximate | Failed | Not run | Not run | Not run | Not 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 engines | Not run | Not run | Not counted | Not run | Not run | Not counted | Not run | Not 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 engines | Not run | Not run | Measured†, approximate | Not run | Not run | Not counted | Not run | Not 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 engines | Not run | Not counted | Not counted | Unsupported | Unsupported | Not counted | Not counted | Measured†, approximate |
| LFM2.5 2.6B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 Not counted: fewer than two scored engines | Not run | Not counted | Not counted | Unsupported | Unsupported | Not counted | Not counted | Measured†, approximate |
| LFM2.5 2.6B on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Not run | Not counted | Not run | Not run | Not run | Not run | Measured†, approximate |
| LFM2.5 2.6B on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Not run | Not counted | Not run | Not run | Not run | Not run | Measured†, approximate |
| LFM2.5 350M on OnePlus 13 · 16 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not counted | Not run | Measured†, approximate | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 350M on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not counted | Not run | Measured†, approximate | Not run | Not run | Not run | Not run | Not counted |
| 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 engines | Not counted | Not run | Not counted | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 2.6B on Pixel 8 · 8 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Not run | Failed | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 2.6B on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Not run | Not counted | Not run | Not run | Not run | Not run | Measured†, approximate |
| LFM2.5 350M on Pixel 8 · 8 GB 4-bit · Archive 2048 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not counted | Not run | Not counted | Not run | Not run | Not run | Not run | Not counted |
| LFM2.5 350M on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not counted | Not run | Measured†, approximate | Not run | Not run | Not run | Not run | Not counted |
Each engine’s Speed score in each matched comparison, out of 100, or why it has none. How rankings work