Explore benchmarks
Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.
Top Engines
Not enough eligible results to rank.
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 | 908/8 out of 100, in 8 of 8 comparisons | 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. |
| Magnitude | 974/8 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 | 1006/8 out of 100, in 6 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Ollama | 956/8 out of 100, in 6 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| Rapid-MLX | 994/8 out of 100, in 4 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
| ZML | 724/8 out of 100, in 4 of 8 comparisons | Not measured on this device. | Not measured on this device. | Not measured on this device. |
Speed
| Rank | Engine | Decode and TTFT |
|---|---|---|
| Not ranked | llama.cpp | Unsupported |
details
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · bf16 · Archive 256 input / 128 output · iOS 27
Medians with the model warmed; model loading is excluded. Each table uses one matched comparison.
llama.cpp: llama.cpp errored on the opposite check in qualification: The app wrote no result for run (exit 1); iOS ends an app that exceeds its memory limit or leaves the foreground.
Memory usage by engine
| Rank | Engine | Memory |
|---|---|---|
| Not ranked | llama.cpp | Unsupported |
details
LFM2.5 1.2B Instruct on iPhone 12 · 4 GB · bf16 · Archive 256 input / 128 output · iOS 27
Memory ranks require comparable, calibrated measurements. Unavailable measurements remain unranked.
llama.cpp: llama.cpp errored on the opposite check in qualification: The app wrote no result for run (exit 1); iOS ends an app that exceeds its memory limit or leaves the foreground.
Every comparison
| Comparison | llama.cpp |
|---|---|
| LFM2.5 1.2B Instruct on iPhone 12 · 4 GB bf16 · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored engines | Unsupported |
| 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 | Unsupported |
| LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 2048 input / 128 output · iOS 27 Not counted: fewer than two scored engines | Measured |
| LFM2.5 350M on iPhone 12 · 4 GB bf16 · Archive 256 input / 128 output · iOS 27 Not counted: fewer than two scored engines | Measured |
Each engine’s Speed score in each matched comparison, out of 100, or why it has none. How rankings work