LFM2.5 2.6B on OnePlus 13 · 16 GB

Experiment Complete Published

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

LFM2.5 2.6B as litert-int4 (4-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 02:49 UTC by Glenn Sonna, Xybrid.

Eligible for ranking when the objective's required metrics are measured and this configuration is selected.Approximate comparison: The experiments use different effective KV cache precision: litert-lm default, f16. The experiments here use different 4-bit schemes: litert-int4, Q4_K_M.

Experiment id s4-oneplus13-lfm2.5-2.6b-4-bit-litert-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 better23.8 23.4–25.5 24.2 ± 0.9 23.7–24.9
Time to first token ms, lower is betterNot measured
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better53.5 51.1–69.4 57.8 ± 8.0 53.1–63.3

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 recorded53.6256 tok in 4,774 ms, engine23.7127 tok in 5,367 ms, enginenot recorded40.6 °C, nominal → 40.8 °C, nominal
2not recorded53.0256 tok in 4,831 ms, engine23.8127 tok in 5,337 ms, enginenot recorded39.5 °C, nominal → 39.9 °C, nominal
3not recorded51.1256 tok in 5,010 ms, engine23.4127 tok in 5,419 ms, enginenot recorded39.5 °C, nominal → 39.8 °C, nominal
4not recorded69.4256 tok in 3,691 ms, engine25.5127 tok in 4,990 ms, enginenot recorded40.2 °C, nominal → 41.3 °C, nominal
5not recorded53.3256 tok in 4,803 ms, engine23.8127 tok in 5,334 ms, enginenot recorded39.3 °C, nominal → 39.8 °C, nominal
6not recorded66.6256 tok in 3,844 ms, engine25.2127 tok in 5,038 ms, enginenot recorded40.1 °C, nominal → 41.1 °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 2.6B (LFM2.5, 2.6B)
Upstream
LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
Weights
litert-community/LFM2.5-2.6B@8f87ecede9509fd8d12c3e5b8c46b04b597febfc
Format
litertlm
File 1
LFM2.5-2.6B_int4.litertlm · 1.55 GiB · sha256 7e2194cd81cd82bcbdd6029b3509d99f49c1782afbdfc98c0e4b29b9cc04e6a6
File 2
README.md · 18,500 bytes · sha256 ad39356f0ce401994fed4791f08a33353db1c6e078358f000d3ddcc8ff756bbb
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 256 input / 128 output
Prompt
256 tokens, from prompts/source.txt
Prompt SHA-256
c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
Chat template
ea663864491de7ade391839479860ca95541f892f72665c73251fbd4643b1bef
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
38.6 °C, nominal
Thermal at end
41.2 °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, 02:49 UTC
Harness
xybrid-bench 0.4.0 (0d0ba6145754774719663a31a97e275409f98a2f)
Methodology
v0.6
Publication
published
Published
16 Nov 2026, 10:23 UTC
Reviewed by
Glenn Sonna

Output check

Result
Passed
Method
sanity-v1-bf16-reference
Reference
checks/sanity-v1.json
Reference SHA-256
a702dee079525ae0ec90465b1c9e26052c99cb3e1c53e83dea05be4c194fc7ca
Required passing checks
8
Check arithmetic
Passed · sha256 90a647b2379fe43265d36db39c01e0d324059b2e48f24ec4e2c1f6ec1c0d21eb
Check capital
Passed · sha256 7a3bb1905f2039638dff3f8a3da57abf7b1da32596b04c5ed04c5296f155196a
Check opposite
Passed · sha256 69a13e1ba8e284fcc26068ec8aa80e8a7e7f8bbebe86dc7a45424411198a6859
Check weekday
Passed · sha256 b8c6a621f6e216db1d214b8d906c759be744ff3abc6e41f979ff0d24575cbbcd
Check color
Failed · sha256 e7cb21de52f71fbf3756d3e7fbeec92e8b5fa123b1a21476d1fd59911201f7d1
Check sort
Failed · sha256 15f349e050f6fd4d9c4f893f73af531ddb5d7b6242c4516df6401d3df0f653f3
Check animal
Failed · sha256 aaf458b3b76ec5162e6ac43bee3ea73000738a3f4fe5c0316852d2f99886fce3
Check word
Passed · sha256 2e1816dd952a0d4c672ad52a4f32599d4eb0477bf5798060b93fe68f7684dbbd
Check copy
Passed · sha256 d8c711dfa5fef68d1d0f86320daeca065b91bc8d0dbcea210f8b9ef80eefc6c2
Check needle-start
Passed · sha256 56a69645d0ff053b3b7001c224f07a374bf963a22c9fa4706dda5e56e3616870
Check needle-end
Passed · sha256 34b7b9e17d75628c346994d8be48566a2dd011ba8533dc75fc33a579ee705365
Check continuation-128
Passed · sha256 fe1fdf5d49caa68c1ef2f8a341413cb2c3826023aef1113c6c289dcd86193b32
Detail
8/9 of the checks the model passes at BF16; needs 8 and the mandatory ones (needle-start, continuation-128). Left out, failed by every BF16 configuration: color, sort, needle-end.

Reproduce it

Commands
pnpm bench run --plan plans/s4-oneplus13-lfm2.5-2.6b-4-bit.json

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

Raw data