Rankings

Explore benchmarks

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

Top Engines

Top Engines, Desktop, Speed score.
#EngineSpeed score out of 100
1Ollama Ollama 100 /100 Score
2llama.cpp ggml-org 96 /100 Score
Not ranked in this view
Not rankedMagnitude Magnitude Unsupported
Not rankedZML ZML Unsupported
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

Magnitude: Unsupported in 1 comparison. Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

ZML: Unsupported in 1 comparison. zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).

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.cpp96 out of 100, in 1 of 1 comparisons
Ollama100 out of 100, in 1 of 1 comparisons
MagnitudeUnsupported Unsupported in 1 comparison. Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).
ZMLUnsupported Unsupported in 1 comparison. zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).

Speed

TTFT ms

Generation tok/s

Speed, LFM2.5 2.6B on M5 Max · 64 GiB, bf16 · Archive 256 input / 128 output · macOS 27
RankEngineDecode and TTFT
1Ollama Ollama91.7 tok/s 57.0 ms TTFT
2llama.cpp ggml-org88.1 tok/s 68.8 ms TTFT
Not rankedMagnitude MagnitudeUnsupported
Not rankedZML ZMLUnsupported
details

LFM2.5 2.6B on M5 Max · 64 GiB · bf16 · Archive 256 input / 128 output · macOS 27

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

Magnitude: Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

ZML: zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).

Memory usage by engine

Memory usage by engine, LFM2.5 2.6B on M5 Max · 64 GiB, bf16 · Archive 256 input / 128 output · macOS 27
RankEngineMemory
1Ollama Ollama5.31 GiB
2llama.cpp ggml-org5.31 GiB
Not rankedMagnitude MagnitudeUnsupported
Not rankedZML ZMLUnsupported
details

LFM2.5 2.6B on M5 Max · 64 GiB · bf16 · Archive 256 input / 128 output · macOS 27

Memory ranks require comparable, calibrated measurements. Unavailable measurements remain unranked.

Magnitude: Magnitude's chat API renders LFM2.5 2.6B's own template, which always opens a thinking block, so it streams reasoning and can't run the closed-think prompts (measured in qualification).

ZML: zml can't run the frozen prompts: Error: LLMD streamed reasoning before its answer; the harness can't time it apart from the answer (measured in qualification).

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
ComparisonOllamallama.cppMagnitudeZML
LFM2.5 2.6B on M5 Max · 64 GiB bf16 · Archive 256 input / 128 output · macOS 27 10096UnsupportedUnsupported

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