LFM2.5 350M on OnePlus 13 · 16 GB

Experiment Complete Published

LiteRT-LM 0.19.0 on OnePlus 13 · 16 GB, CPU

LFM2.5 350M as litert-int4 (4-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 12 Nov 2026, 14:48 UTC by Glenn Sonna, Xybrid.

Doesn’t count in rankings: Its output check failed: 6/8 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-litert-2048

Summary

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

MetricMedianRangeMean ± SDQuartiles
Decode speed tok/s, higher is better92.8 88.4–97.1 93.0 ± 3.1 91.5–95.2
Time to first token ms, lower is betterNot measured
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better527.5 526.1–530.4 527.9 ± 1.5 527.1–528.7

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 recorded527.42,048 tok in 3,883 ms, engine88.4127 tok in 1,437 ms, enginenot recorded36.9 °C, nominal → 37.9 °C, nominal
2not recorded530.42,048 tok in 3,861 ms, engine95.7127 tok in 1,327 ms, enginenot recorded35.0 °C, nominal → 36.4 °C, nominal
3not recorded526.12,048 tok in 3,893 ms, engine93.6127 tok in 1,356 ms, enginenot recorded34.9 °C, nominal → 36.3 °C, nominal
4not recorded529.02,048 tok in 3,871 ms, engine91.4127 tok in 1,390 ms, enginenot recorded34.9 °C, nominal → 36.4 °C, nominal
5not recorded527.02,048 tok in 3,886 ms, engine92.0127 tok in 1,380 ms, enginenot recorded34.9 °C, nominal → 36.4 °C, nominal
6not recorded527.62,048 tok in 3,882 ms, engine97.1127 tok in 1,308 ms, enginenot recorded35.0 °C, nominal → 36.4 °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
LiteRT-LM
Maintainer
Google AI Edge
License
Apache-2.0, open source
Version
0.19.0
Commit
Not recorded
Binary SHA-256
8e199c6b3fb438cb94943567a279f9e1f994d57c3e1f4667084fc8ae2d06a6eb
Built from
release
Build flags
None
Backend
CPU
Threads
Not recorded
Interface
cli
Settings in effect
backend=cpu process=one per generation chat_template=none (session API) sampler=top_k=1 temperature=0 launch.max_num_tokens=4096 launch.num_cpu_threads=engine default launch.cache_dir=/data/local/tmp/xybrid/litert-cache launch.benchmark=true launch.benchmark_prefill_tokens=0 launch.benchmark_decode_tokens=0 launch.async=false

Model and weights

Base model
LFM2.5 350M (LFM2.5, 350M)
Upstream
LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
Weights
litert-community/LFM2.5-350M@4754bf697659039afee2962cfd9c8f40d547ab35
Format
litertlm
File 1
LFM2.5-350M_int4.litertlm · 236.3 MiB · sha256 c29a41cdf4148ec9f4b6e57f8e598728a05a189fdc7ca0764b013b78f9dfd52f
File 2
README.md · 14,806 bytes · sha256 4aa8f3ef769b89ecf207b1506da4a8c617cd7aafbcf9520a96ae2e10f1a6bc56
Quantization
litert-int4 (4-bit)
Weight bits
4
Group size
Not recorded
KV cache
litert-lm default
Conversion
Published upstream by litert-community
Conversion command
Not recorded

Workload

Workload
Archive 2048 input / 128 output
Prompt
2,048 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
31.4 °C, nominal
Thermal at end
36.5 °C, nominal
Thermal gate
Android thermal status none (0)
Throttling detected
No

Provenance

Measured by
Glenn Sonna, Xybrid
Operator affiliation
Xybrid
Run at
12 Nov 2026, 14:48 UTC
Harness
xybrid-bench 0.4.0 (9debd9525d34af7f4ef03e3c43e265a0a7bfb1fa)
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 4a44dc15364204a80fe80e9039455cc1608281820fe2b24f1e5233ade6af1dd5
Check capital
Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
Check opposite
Passed · sha256 f151cd9e12c8994edfa316e4624f956bc68460454869177f287146f8cc956a12
Check weekday
Failed · sha256 6a00dfc1dc867e8454c2c8856e1512d9bf02a76710e3411c0972aec886c76c61
Check color
Passed · sha256 d486dfbd5fb578340bccbdd0a662527eab38550648d5f44517e5ac71b8824703
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
Failed · sha256 7847505d933db2323908d71428d5f0a65999bbad0a763b4574e8cf5a8a469b7a
Detail
6/8 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.json

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

Raw data