Explore this comparison’s ranking

Comparison Counted

Which engine runs LFM2.5 350M best on OnePlus 13 · 16 GB?

Device
OnePlus 13 · 16 GB (Android phones)
OS
Android 16
Model
LFM2.5 350M, 350M parameters
Weights
8-bit
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 350M best on OnePlus 13 · 16 GB? Ranked by Speed.
#EngineDecode and First token
1llama.cpp, an approximate comparison, see details ggml-org Decode: 100.1 tok/s 1,648 ms first token
2LiteRT-LM, an approximate comparison, see details Google AI Edge Decode: 76.5 tok/s First token not measured
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

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

† LiteRT-LM: approximate comparison. The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.

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
llama.cpp b12110 · CPU · Q8_0 Eligible, approximately: The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.100.1 range99.1–101.71,648 range1,587–1,673Not measured1,252 range1,230–1,2986of 6 planned
LiteRT-LM 0.19.0 · CPU · litert-int8 Eligible, approximately: The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 8-bit schemes: litert-int8, Q8_0.76.5 range74.4–76.7Not measuredNot measured851.6 range841.9–859.76of 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-oneplus-13--android-16--lfm2.5-350m--8-bit--archive-2048-128.