LFM2.5 350M on OnePlus 13 · 16 GB

Experiment Complete Published

ExecuTorch 1.6.0 on OnePlus 13 · 16 GB, CPU

LFM2.5 350M as 8da4w (4-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 05:59 UTC by Glenn Sonna, Xybrid.

Doesn’t count in rankings: Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.

Experiment id s4-oneplus13-lfm2.5-350m-4-bit-et-xnnpack-256

Summary

Over 6 valid trials of 6 attempted (6 planned), computed from the raw trials below.

MetricMedianRangeMean ± SDQuartiles
Decode speed tok/s, higher is better203.0 199.7–204.5 202.8 ± 1.7 202.6–203.8
Time to first token ms, lower is betterNot measured
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better1,524 1,471–1,662 1,545 ± 70.1 1,502–1,576

Trials, metric by metric

The line runs from the lowest to the highest valid trial, the dot is the median and each tick is one trial.

Decode speed tok/s, higher is better
Time to first token ms, lower is better
Peak memory GiB, lower is better
Prefill speed tok/s, higher is better

Every trial

Raw token counts and durations, with the speeds computed from them. Invalid trials stay in the record with their reason; they are left out of the summary, never silently dropped.

Every attempted trial
TrialTime to first token msPrefill tok/sDecode tok/sPeak memory GiBThermalNote
1not recorded1,471256 tok in 174 ms, engine202.6127 tok in 627 ms, enginenot recorded30.7 °C, nominal → 31.0 °C, nominal
2not recorded1,590256 tok in 161 ms, engine204.5127 tok in 621 ms, enginenot recorded28.1 °C, nominal → 28.5 °C, nominal
3not recorded1,533256 tok in 167 ms, engine203.9127 tok in 623 ms, enginenot recorded27.8 °C, nominal → 28.2 °C, nominal
4not recorded1,497256 tok in 171 ms, engine203.5127 tok in 624 ms, enginenot recorded27.8 °C, nominal → 28.2 °C, nominal
5not recorded1,515256 tok in 169 ms, engine202.6127 tok in 627 ms, enginenot recorded27.8 °C, nominal → 28.2 °C, nominal
6not recorded1,662256 tok in 154 ms, engine199.7127 tok in 636 ms, enginenot recorded27.9 °C, nominal → 28.3 °C, nominal

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.

Configuration

Device

Device
OnePlus CPH2655
Cohort
Android phones (mobile)
SoC
Qualcomm Snapdragon 8 Elite (SM8750)
CPU
8-core Oryon CPU (2× 4.32 GHz, 6× 3.53 GHz)
GPU
Adreno 830
NPU
Hexagon
RAM
16.00 GiB
OS
Android 16 (BP2A.250605.015)
Kernel
6.6.89-android15-8-g5a0ffb447c1d-ab13771415-4k
Power
usb
Low power mode
No
Wakefulness
awake

Engine

Engine
ExecuTorch
Maintainer
PyTorch (Meta)
License
BSD-3-Clause, open source
Version
1.6.0
Commit
4776f71b6f0daa5dfc7d758d5836fc1cc0d40154
Binary SHA-256
a214c779c6d098e58572ee7c3c22494afc81a5ad50cbc0fd68d1049f3d872b5a
Built from
source
Build flags
None
Backend
CPU
Threads
Not recorded
Interface
cli
Settings in effect
backend=cpu recipe=lfm2.5-350m-et-xnnpack-8da4w,lfm2_xnnpack_q8da4w.yaml,lfm2.5-350m-et-xnnpack-8da4w.pte runner=xybrid_et_runner process=one per generation echo=false temperature=0 num_bos=0 num_eos=0 reset_before_generation=true eos_ignorable=false threads=engine default (performance cores)

Model and weights

Base model
LFM2.5 350M (LFM2.5, 350M)
Upstream
LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
Weights
LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
Format
pte
File 1
lfm2.5-350m-et-xnnpack-8da4w.pte · 434.9 MiB · sha256 9742351692899c943bf1016142451cd048ead5031b5bea0d3b4ad54b355cdecd
File 2
tokenizer.json · 4.5 MiB · sha256 df1d8d5ec5d091b460562ffd545e4a5e91d17d4a0db7ebe733be34ed374377bd
Quantization
8da4w (4-bit)
Weight bits
4
Group size
Not recorded
KV cache
fp32
Conversion
Converted by Xybrid with executorch export_llm 1.6.0
Conversion command
cd "$ROOT/engines/executorch/build/lfm2.5-350m-et-xnnpack-8da4w" && PYTHONPATH="$ROOT/engines/executorch/.venv/lib/python3.12/site-packages/executorch" "$ROOT/engines/executorch/.venv/bin/python" -m executorch.extension.llm.export.export_llm --config "$ROOT/engines/executorch/.venv/lib/python3.12/site-packages/executorch/examples/models/lfm2/config/lfm2_xnnpack_q8da4w.yaml" +base.model_class=lfm2_5_350m "+base.checkpoint=$ROOT/engines/executorch/build/lfm2.5-350m-canonical.pth" "+base.params=$ROOT/downloads/executorch/4776f71b6f0daa5dfc7d758d5836fc1cc0d40154/examples/models/lfm2/config/lfm2_5_350m_config.json" +export.max_seq_length=4096 +export.max_context_length=4096 +export.output_name=lfm2.5-350m-et-xnnpack-8da4w.pte

Workload

Workload
Archive 256 input / 128 output
Prompt
256 tokens, from prompts/source.txt
Prompt SHA-256
c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
Chat template
ba551d58630afa3190b1be3602e28301f3d2e9bbac978dfc49d6d825171648b6
Output
128 tokens, ignoring end of sequence
Context length
4,096
Batch size
1
Sampling
Greedy
Timing
One streamed request per trial
Warmup
2 runs, not counted
Trials planned
6
Cooldown
60 s between trials

Conditions

Ambient
Not recorded
Thermal at start
28.4 °C, nominal
Thermal at end
28.3 °C, nominal
Thermal gate
Android thermal status none (0)
Throttling detected
No

Provenance

Measured by
Glenn Sonna, Xybrid
Operator affiliation
Xybrid
Run at
13 Nov 2026, 05:59 UTC
Harness
xybrid-bench 0.4.0 (620585c98483858dace01a0fa8fa1cb2b15beed6)
Methodology
v0.6
Publication
published
Published
16 Nov 2026, 10:23 UTC
Reviewed by
Glenn Sonna

Output check

Result
Failed
Method
sanity-v1-bf16-reference
Reference
checks/sanity-v1.json
Reference SHA-256
a702dee079525ae0ec90465b1c9e26052c99cb3e1c53e83dea05be4c194fc7ca
Required passing checks
7
Check arithmetic
Failed · sha256 e629fa6598d732768f7c726b4b621285f9c3b85303900aa912017db7617d8bdb
Check capital
Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
Check opposite
Failed · sha256 0b0fd31e2478cff0d3c5bf526a0f8f1c780abfb435eec0a8f2c9beed0eaa6bc4
Check weekday
Passed · sha256 7d8af1de1262f150187d5938bf649d6c35726970685f916d1ec6392a801b9762
Check color
Failed · sha256 ec7d56a01607001e6401366417c5e2eb00ffa0df17ca1a9a831e0b32c8f11bf7
Check sort
Failed · sha256 0ca7eabde70df147ffea0ec2627afd6c362a0bfc80b48981b8880485cca2360e
Check animal
Failed · sha256 d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35
Check word
Failed · sha256 f61e68691bdd0f5ebd3252de0396569d624bd2fba240d66fae90edb456a9f48f
Check copy
Passed · sha256 d61e6890d0e3571b0c7693612d41f8d059a1fcdef4ba959c0af4144541d41907
Check needle-start
Passed · sha256 8b9af2e5b8b4cfddb87d171997b95c471f8d68a68e30fb5177abeb3332372edd
Check needle-end
Passed · sha256 e6589c736af32f81bf239c5eda6de41959122ccc1d05463b75e0eb0c70fc831c
Check continuation-128
Passed · sha256 46e2ace9e836d0de7961085acc08170024e02dee11c4040d0a28e45dade9f606
Detail
5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.

Reproduce it

Commands
pnpm bench run --plan plans/s4-oneplus13-lfm2.5-350m-4-bit-et.json

Three palindromic blocks per quantization class and workload; load, two warmups, one trial, unload per turn.

Raw data