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 | llama.cpp†, an approximate comparison, see details | 88 /100 Score |
| ||
| 2 | LiteRT-LM†, an approximate comparison, see details | 57 /100 Score |
| ||
| Not ranked in this view | ||
| Not ranked | MLX LM | Too few results |
| Not ranked | Ollama | Too few results |
| Not ranked | uzu | Too few results |
| Not ranked | Rapid-MLX | Too few results |
| Not ranked | Magnitude | 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.
† llama.cpp: approximate comparison. 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: litert-lm default, f16, magnitude default, model-dtype, uzu 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: f16, model-dtype. 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, magnitude default, model-dtype, uzu default. Its weights are 8-bit in another scheme: litert-int8, where most use Q8_0. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.
MLX LM: Results in 8 of 18 comparisons; a rank needs 9.
Ollama: Results in 8 of 18 comparisons; a rank needs 9.
uzu: Results in 7 of 18 comparisons; a rank needs 9.
Rapid-MLX: Results in 6 of 18 comparisons; a rank needs 9.
Magnitude: Results in 4 of 18 comparisons; a rank needs 9.
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 | 878/8 out of 100, in 8 of 8 comparisons | 1004/4 out of 100, in 4 of 4 comparisons | 893/3 out of 100, in 3 of 3 comparisons | 763/3 out of 100, in 3 of 3 comparisons |
| LiteRT-LM | 284/8 out of 100, in 4 of 8 comparisons | 784/4 out of 100, in 4 of 4 comparisons | 983/3 out of 100, in 3 of 3 comparisons | Not measured on this device. |
| uzu | 994/8 out of 100, in 4 of 8 comparisons | Not measured on this device. | Not measured on this device. | 1003/3 out of 100, in 3 of 3 comparisons |
| Magnitude | 924/8 out of 100, in 4 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| MLX LM | 968/8 out of 100, in 8 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Ollama | 898/8 out of 100, in 8 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Rapid-MLX | 966/8 out of 100, in 6 of 8 comparisons | 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 | 25.7 tok/s 1,048 ms TTFT |
| 2 | llama.cpp†, approximate comparison, see details | 24.1 tok/s 938 ms TTFT |
details
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · 8-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: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.
llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.
Memory usage by engine
| Rank | Engine | Memory |
|---|---|---|
| Not ranked | llama.cpp | Not measured |
| Not ranked | uzu | Not measured |
details
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · 8-bit · Archive 256 input / 128 output · iOS 27
Memory ranks require comparable, calibrated measurements. Unavailable measurements remain unranked.
llama.cpp: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.
uzu: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: f16, uzu default. The experiments here use different 8-bit schemes: Q8_0, mirai-l.
Every comparison
| Comparison | llama.cpp | LiteRT-LM | MLX LM | Ollama | uzu | Rapid-MLX | Magnitude |
|---|---|---|---|---|---|---|---|
| LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 | 94†, approximate | Not run | Not run | Not run | 100†, approximate | Not run | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 2048 input / 128 output · iOS 27 | 69†, approximate | Not run | Not run | Not run | 100†, approximate | Not run | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 | 67†, approximate | Not run | Not run | Not run | 100†, approximate | Not run | Not run |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 | 87†, approximate | 32†, approximate | 92†, approximate | 87†, approximate | 100†, approximate | 92†, approximate | 89†, approximate |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 87†, approximate | 32†, approximate | 96†, approximate | 87†, approximate | 100†, approximate | 97†, approximate | 88†, approximate |
| LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 | 89†, approximate | Not counted | 100†, approximate | 96†, approximate | Unsupported | 100†, approximate | Unsupported |
| LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 91†, approximate | Not counted | 100†, approximate | 95†, approximate | Unsupported | 100†, approximate | Unsupported |
| LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 | 76†, approximate | 26†, approximate | 90†, approximate | 77†, approximate | 100†, approximate | 92†, approximate | 96†, approximate |
| LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 75†, approximate | 24†, approximate | 100†, approximate | 77†, approximate | 97†, approximate | 98†, approximate | 93†, approximate |
| Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 2048 input / 128 output · macOS 27 | 98†, approximate | Not run | 97†, approximate | 100†, approximate | Unsupported | Not run | Unsupported |
| Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 98†, approximate | Not run | 97†, approximate | 100†, approximate | Unsupported | Not run | Unsupported |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 | 100†, approximate | 87†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 | 100†, approximate | 86†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 2048 input / 128 output · Android 16 | 100†, approximate | 76†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 350M on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 | 100†, approximate | 64†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 | 87†, approximate | 100†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 2048 input / 128 output · Android 16 | 81†, approximate | 100†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 350M on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 | 100†, approximate | 93†, approximate | Not run | Not run | Not run | Not run | Not 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 engines | Measured†, approximate | Not run | Not run | Not run | Not counted | Not run | Not 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 engines | Unsupported | Not run | Not run | Not run | Unsupported | Not run | Not 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 engines | Unsupported | Not run | Not run | Not run | Unsupported | Not run | Not 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 engines | Measured†, approximate | Not counted | Not run | Not run | Not run | Not run | Not 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 engines | Measured†, approximate | Not counted | Not run | Not run | Not run | Not run | Not 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 engines | Measured†, approximate | Not counted | Not run | Not run | Not run | Not run | Not 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 engines | Failed | Failed | Not run | Not run | Not run | Not run | Not 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 engines | Not counted | Not counted | Not run | Not run | Not run | Not run | Not run |
Each engine’s Speed score in each matched comparison, out of 100, or why it has none. How rankings work