LFM2.5 1.2B Instruct on Pixel 8 · 8 GB

Experiment Partial Published

LiteRT-LM 0.19.0 on Pixel 8 · 8 GB, CPU

LFM2.5 1.2B Instruct as litert-int8 (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 01:05 UTC by Glenn Sonna, Xybrid.

Doesn’t count in rankings: Partial: 5 of 6 planned trials were valid.

Experiment id s4-pixel8-lfm2.5-1.2b-8-bit-litert-2048

Errors

  • trial: No trial was valid.

Summary

Over 5 valid trials of 6 attempted (6 planned), computed from the raw trials below.

MetricMedianRangeMean ± SDQuartiles
Decode speed tok/s, higher is better16.0 15.0–16.1 15.8 ± 0.4 16.0–16.0
Time to first token ms, lower is betterNot measured
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better150.4 146.7–161.7 153.2 ± 7.1 147.4–159.9

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
1Invalidnot recorded148.92,048 tok in 13,752 ms, engine15.4127 tok in 8,272 ms, enginenot recorded38.8 °C, nominal → 39.0 °C, lightThe measurement interval lacks nominal thermal evidence or reported throttling. The device reported thermal throttling during the trial.
2not recorded150.42,048 tok in 13,619 ms, engine15.0127 tok in 8,442 ms, enginenot recorded38.4 °C, nominal → 38.9 °C, nominal
3not recorded147.42,048 tok in 13,897 ms, engine16.0127 tok in 7,929 ms, enginenot recorded38.5 °C, nominal → 39.0 °C, nominal
4not recorded146.72,048 tok in 13,958 ms, engine16.1127 tok in 7,908 ms, enginenot recorded38.6 °C, nominal → 39.0 °C, nominal
5not recorded159.92,048 tok in 12,812 ms, engine16.0127 tok in 7,946 ms, enginenot recorded38.6 °C, nominal → 39.2 °C, nominal
6not recorded161.72,048 tok in 12,667 ms, engine16.0127 tok in 7,952 ms, enginenot recorded38.4 °C, nominal → 39.1 °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
Google Pixel 8
Cohort
Android phones (mobile)
SoC
Google Tensor G3
CPU
9-core CPU (1× Cortex-X3, 4× Cortex-A715, 4× Cortex-A510)
GPU
Arm Mali-G715
NPU
Not recorded
RAM
8.00 GiB
OS
Android 16 (CP1A.260505.005)
Kernel
6.1.145-android14-11-gfa1d6308d1fe-ab14691759
Power
mains
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 1.2B Instruct (LFM2.5, 1.2B)
Upstream
LiquidAI/LFM2.5-1.2B-Instruct@b9d816ab510f9a28dca37cb182e9da8b0226e13c
Weights
litert-community/LFM2.5-1.2B-Instruct@4a148a1032ce264346c6a2a2931e8d0391dbe5d1
Format
litertlm
File 1
LFM2.5-1.2B-Instruct_int8.litertlm · 1.16 GiB · sha256 ed8201f88a1a116218bf03cf7cc5c33accdc2f6f502aa8d682f616beea1ec870
File 2
README.md · 20,979 bytes · sha256 531c7c0863478b158f7cdf91c3af2a51b26bcd0081b3c976b9aeabe9280dbab6
Quantization
litert-int8 (8-bit)
Weight bits
8
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
35.4 °C, nominal
Thermal at end
39.1 °C, nominal
Thermal gate
Android thermal status none (0)
Throttling detected
Yes

Provenance

Measured by
Glenn Sonna, Xybrid
Operator affiliation
Xybrid
Run at
13 Nov 2026, 01:05 UTC
Harness
xybrid-bench 0.4.0 (e5cc97760a61b69ce4afa7641ca1b9106cc12a4a)
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
11
Check arithmetic
Passed · sha256 6b51d431df5d7f141cbececcf79edf3dd861c3b4069f0b11661a3eefacbba918
Check capital
Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
Check opposite
Passed · sha256 f151cd9e12c8994edfa316e4624f956bc68460454869177f287146f8cc956a12
Check weekday
Passed · sha256 7d8af1de1262f150187d5938bf649d6c35726970685f916d1ec6392a801b9762
Check color
Failed · sha256 19dd83f117525b931fccdafe808aaa6939af792ee549f359eff13fac0d622f5d
Check sort
Passed · sha256 a386b3c9b4b4786df5bb6474bab0a62b8476e2f3f9c8a6433aca40152840f6b7
Check animal
Passed · sha256 4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a
Check word
Passed · sha256 3b635d3b4437e023e72a9df26201b6ab51285b376446446ebb379121994550f6
Check copy
Passed · sha256 d61e6890d0e3571b0c7693612d41f8d059a1fcdef4ba959c0af4144541d41907
Check needle-start
Passed · sha256 8b9af2e5b8b4cfddb87d171997b95c471f8d68a68e30fb5177abeb3332372edd
Check needle-end
Passed · sha256 e6589c736af32f81bf239c5eda6de41959122ccc1d05463b75e0eb0c70fc831c
Check continuation-128
Passed · sha256 fe1fdf5d49caa68c1ef2f8a341413cb2c3826023aef1113c6c289dcd86193b32
Detail
11/12 of the checks the model passes at BF16; needs 11 and the mandatory ones (needle-start, needle-end, continuation-128). Left out, failed by every BF16 configuration: none.

Reproduce it

Commands
pnpm bench run --plan plans/s4-pixel8-lfm2.5-1.2b-8-bit.json

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

Raw data