Explore this comparison’s ranking

Comparison Counted

Which engine runs LFM2.5 2.6B best on M5 Max · 64 GiB?

Device
M5 Max · 64 GiB (Apple silicon Macs)
OS
macOS 27
Model
LFM2.5 2.6B, 2.6B parameters
Weights
bf16
Workload
Archive 2048 input / 128 output: 2,048 tokens in, 128 out
Decoding
Greedy, batch 1, context 4,096
Power
Plugged in

Speed: Decode speed: tokens generated per second.

Which engine runs LFM2.5 2.6B best on M5 Max · 64 GiB? Ranked by Speed.
#EngineDecode and First token
1Ollama Ollama Decode: 91.1 tok/s 289 ms first token
2llama.cpp ggml-org Decode: 88.7 tok/s 305 ms first token
Not ranked in this view
Not rankedMagnitude Magnitude Unsupported 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).
Not rankedZML ZML Unsupported 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).
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

Every experiment

Medians over valid trials, with the lowest and highest beneath. Eligible experiments are complete and passed their output check. The ranking above selects each engine's configuration for this objective when its required metrics are measured.

Every experiment in this comparison
ExperimentRanking eligibilityDecode tok/s, higher is betterFirst token ms, lower is betterMemory GiB, lower is betterPrefill tok/s, higher is betterValid trials
Ollama 0.40.13 · Metal · BF16 Eligible91.1 range90.0–91.5289 range287–2905.33 range5.33–5.337,147 range7,127–7,1966of 6 planned
llama.cpp b12110 · Metal · BF16 Eligible88.7 range86.0–88.9305 range304–3065.33 range5.33–5.336,728 range6,704–6,7616of 6 planned
Magnitude 0.2.17 · Metal · BF16 Unsupported 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).––––0of 6 planned
ZML 20261106.0 · Metal · BF16 Unsupported 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).––––0of 6 planned

Every trial, metric by metric

The line runs from an experiment's lowest to its highest valid trial, the dot is the median and each tick is one trial. Every scale starts at zero.

Caveats

  • Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
  • Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.

About this comparison

Worked out from its experiments: every experiment here shares the device, the OS major version, the power state, the base model, the quantization class and the workload. Measured under methodology v0.6. Comparison id glenn-m5-max-64gb--macos-27--lfm2.5-2.6b--bf16--archive-2048-128.