Rankings

Explore benchmarks

Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.

Top Engines

Overall needs mobile results; each platform is ranked on its own until then.

Desktop

Top Engines, Desktop, Speed score.
#EngineSpeed score out of 100
1MLX LM, an approximate comparison, see details Apple (ml-explore) 100 /100 Score
2llama.cpp, an approximate comparison, see details ggml-org 92 /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

† MLX LM: approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

Coverage

Speed score per device, out of 100: each device ranked on its own.
Desktop
M5 Max 64 GiB macOS 27 Apple M5 Max
llama.cpp92 out of 100, in 1 of 1 comparisons
MLX LM100 out of 100, in 1 of 1 comparisons

Speed

Speed, LFM2.5 1.2B Instruct on M5 Max · 64 GiB, bf16 · 2048 input / 128 output · macOS 27
RankEnginePrefill
1MLX LM, approximate comparison, see details Apple (ml-explore)23,503 tok/s
2llama.cpp, approximate comparison, see details ggml-org15,456 tok/s
details

LFM2.5 1.2B Instruct on M5 Max · 64 GiB · bf16 · 2048 input / 128 output · macOS 27

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

MLX LM: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

Memory usage by engine

Memory usage by engine, LFM2.5 1.2B Instruct on M5 Max · 64 GiB, bf16 · 2048 input / 128 output · macOS 27
RankEngineMemory
Not rankedllama.cpp ggml-orgNot measured
Not rankedMLX LM Apple (ml-explore)Not measured
details

LFM2.5 1.2B Instruct on M5 Max · 64 GiB · bf16 · 2048 input / 128 output · macOS 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, model-dtype.

MLX LM: No peak memory measured. † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
Comparisonllama.cppMLX LM
LFM2.5 1.2B Instruct on M5 Max · 64 GiB bf16 · 2048 input / 128 output · macOS 27 92, approximate100, approximate
LFM2.5 1.2B Instruct on M5 Max · 64 GiB 4-bit · 2048 input / 128 output · macOS 27 Not counted: fewer than two scored enginesNot countedNot counted

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