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 | Ollama†, an approximate comparison, see details | 88 /100 Score |
| ||
| 2 | llama.cpp†, an approximate comparison, see details | 83 /100 Score |
| ||
| Not ranked in this view | ||
| Not ranked | MLX LM | Too few results |
| Not ranked | uzu | Too few results |
| Not ranked | LiteRT-LM | Too few results |
| Not ranked | Magnitude | Too few results |
| Not ranked | Rapid-MLX | Too few results |
| Not ranked | ExecuTorch | Too few results |
| Not ranked | 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.
† 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: 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: 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: 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.
MLX LM: Results in 9 of 21 comparisons; a rank needs 11.
uzu: Results in 8 of 21 comparisons; a rank needs 11.
LiteRT-LM: Results in 6 of 21 comparisons; a rank needs 11.
Magnitude: Results in 6 of 21 comparisons; a rank needs 11.
Rapid-MLX: Results in 6 of 21 comparisons; a rank needs 11.
ExecuTorch: Results in 4 of 21 comparisons; a rank needs 11.
ZML: Results in 2 of 21 comparisons; a rank needs 11.
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 | 8411/11 out of 100, in 11 of 11 comparisons | 943/3 out of 100, in 3 of 3 comparisons | 883/3 out of 100, in 3 of 3 comparisons | 694/4 out of 100, in 4 of 4 comparisons |
| LiteRT-LM | 2/11Not ranked. Results in 2 of 11 comparisons; a rank needs 6. | 742/3 out of 100, in 2 of 3 comparisons | 962/3 out of 100, in 2 of 3 comparisons | Not measured on this device. |
| uzu | 4/11Not ranked. Results in 4 of 11 comparisons; a rank needs 6. | Not measured on this device. | Not measured on this device. | 1004/4 out of 100, in 4 of 4 comparisons |
| Magnitude | 896/11 out of 100, in 6 of 11 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| MLX LM | 999/11 out of 100, in 9 of 11 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Ollama | 8811/11 out of 100, in 11 of 11 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Rapid-MLX | 996/11 out of 100, in 6 of 11 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| ExecuTorch | 1/11Not ranked. Results in 1 of 11 comparisons; a rank needs 6. | 1/3Not ranked. Results in 1 of 3 comparisons; a rank needs 2. | 1/3Not ranked. Results in 1 of 3 comparisons; a rank needs 2. | 1/4Not ranked. Results in 1 of 4 comparisons; a rank needs 2. |
| ZML | 2/11Not ranked. Results in 2 of 11 comparisons; a rank needs 6. | 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 | Ollama | llama.cpp | MLX LM | uzu | LiteRT-LM | Magnitude | Rapid-MLX | ExecuTorch | ZML |
|---|---|---|---|---|---|---|---|---|---|
| LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 4-bit · Archive 256 input / 128 output · iOS 27 | Not run | 83†, approximate | Not run | 100†, approximate | Not run | Not run | Not run | 94†, approximate | Not run |
| LFM2.5 1.2B Instruct on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 | Not run | 94†, approximate | Not run | 100†, approximate | Not run | 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 run | 43†, approximate | Not run | 100†, approximate | Not run | Not run | Not run | Not counted | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB 8-bit · Archive 256 input / 128 output · iOS 27 | Not run | 67†, approximate | Not run | 100†, approximate | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | 84†, approximate | 81†, approximate | Not counted | 100†, approximate | Not counted | 82†, approximate | Not counted | 87†, approximate | Not run |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 87†, approximate | 87†, approximate | 96†, approximate | 100†, approximate | 32†, approximate | 88†, approximate | 97†, approximate | Not run | Not run |
| LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 | 100†, approximate | 95†, approximate | 100†, approximate | Not run | Not run | 100†, approximate | 99†, approximate | Not run | 96†, approximate |
| LFM2.5 2.6B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 95†, approximate | 91†, approximate | 100†, approximate | Unsupported | Not counted | Unsupported | 100†, approximate | Not run | Not run |
| LFM2.5 2.6B on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 | 100 | 96 | Not run | Not run | Not run | Unsupported | Not run | Not run | Unsupported |
| LFM2.5 350M on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | 67†, approximate | 62†, approximate | 100†, approximate | 90†, approximate | Not counted | 82†, approximate | 100†, approximate | Not counted | Not run |
| LFM2.5 350M on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 77†, approximate | 75†, approximate | 100†, approximate | 97†, approximate | 24†, approximate | 93†, approximate | 98†, approximate | Not run | Not run |
| LFM2.5 350M on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 | 84†, approximate | 81†, approximate | 100†, approximate | Not run | Not run | 92†, approximate | 98†, approximate | Not run | 73†, approximate |
| Qwen3.8 27B on M5 Max · 64 GiB 4-bit · Archive 256 input / 128 output · macOS 27 | 78†, approximate | 75†, approximate | 100†, approximate | Unsupported | Not run | Unsupported | Not run | Not run | Not run |
| Qwen3.8 27B on M5 Max · 64 GiB 8-bit · Archive 256 input / 128 output · macOS 27 | 100†, approximate | 98†, approximate | 97†, approximate | Unsupported | Not run | Unsupported | Not run | Not run | Not run |
| Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 256 input / 128 output · macOS 27 | 100†, approximate | 95†, approximate | 100†, approximate | Not run | Not run | Unsupported | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 4-bit · Archive 256 input / 128 output · Android 16 | Not run | 83†, approximate | Not run | Not run | Not counted | Not run | Not run | 100†, approximate | Not run |
| LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB 8-bit · Archive 256 input / 128 output · Android 16 | Not run | 100†, approximate | Not run | Not run | 86†, approximate | 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 | Not run | 100†, approximate | Not run | Not run | 64†, approximate | Not run | Not run | Not run | Not run |
| LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 4-bit · Archive 256 input / 128 output · Android 16 | Not run | 78†, approximate | Not run | Not run | Not counted | Not run | Not run | 100†, approximate | Not run |
| LFM2.5 1.2B Instruct on Pixel 8 · 8 GB 8-bit · Archive 256 input / 128 output · Android 16 | Not run | 87†, approximate | Not run | Not run | 100†, approximate | 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 | Not run | 100†, approximate | Not run | Not run | 93†, approximate | Not run | Not run | Not run | Not 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 engines | Not run | Unsupported | Not run | Not run | Not run | 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 counted | Not run | Unsupported | Not run | Not run | Not run | 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 | Not run | Unsupported | Not run | Unsupported | Not run | Not run | Not run | Not run | Not run |
| LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored engines | Not run | Measured | Not run | Not run | Not run | Not run | Not run | Not run | Not 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 engines | Not counted | Not counted | Not counted | Unsupported | Measured†, approximate | Unsupported | Not counted | Not run | Not 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 engines | Not run | Measured | Not run | Not run | Not run | Not run | Not run | Not run | Not 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 engines | Not run | Not counted | Not run | Not run | Measured†, approximate | 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 | Not run | Measured†, approximate | Not run | Not run | Not counted | Not run | Not run | Not run | Not run |
| 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 run | Measured†, approximate | Not run | Not run | Not counted | Not run | Not run | Not counted | Not run |
| LFM2.5 350M on OnePlus 13 · 16 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Measured | Not run | Not run | Not run | Not run | Not run | Not run | Not 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 engines | Not run | Failed | Not run | Not run | Not run | Not run | Not run | Not run | Not 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 engines | Not run | Not counted | Not run | Not run | Measured†, approximate | 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 run | Not counted | Not run | Not run | Not counted | Not run | Not run | Not run | Not run |
| 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 run | Measured†, approximate | Not run | Not run | Not counted | Not run | Not run | Not counted | Not run |
| LFM2.5 350M on Pixel 8 · 8 GB bf16 · Archive 256 input / 128 output · Android 16 Not counted: fewer than two scored engines | Not run | Measured | Not run | Not run | 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