LFM2.5 1.2B Instruct on OnePlus 13 · 16 GB

Experiment Complete Published

llama.cpp b12110 on OnePlus 13 · 16 GB, CPU

LFM2.5 1.2B Instruct as Q8_0 (8-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 00:36 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 8-bit schemes: litert-int8, Q8_0.

Experiment id s4-oneplus13-lfm2.5-1.2b-8-bit-llama-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 better42.1 41.9–42.6 42.1 ± 0.2 42.0–42.2
Time to first token ms, lower is better484 476–555 496 ± 30.1 479–495
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better538.9 467.1–546.9 526.5 ± 30.6 524.5–545.2

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
1555467.1256 tok in 548 ms, engine42.1127 tok in 3,015 ms, enginenot recorded42.5 °C, nominal → 43.1 °C, nominal
2481544.2256 tok in 470 ms, engine42.6127 tok in 2,982 ms, enginenot recorded35.5 °C, nominal → 37.1 °C, nominal
3486533.6256 tok in 480 ms, engine42.2127 tok in 3,011 ms, enginenot recorded35.5 °C, nominal → 37.1 °C, nominal
4479546.9256 tok in 468 ms, engine42.0127 tok in 3,024 ms, enginenot recorded35.7 °C, nominal → 37.3 °C, nominal
5498521.5256 tok in 491 ms, engine41.9127 tok in 3,034 ms, enginenot recorded35.8 °C, nominal → 37.4 °C, nominal
6476545.5256 tok in 469 ms, engine42.1127 tok in 3,016 ms, enginenot recorded36.0 °C, nominal → 37.6 °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
llama.cpp
Maintainer
ggml-org
License
MIT, open source
Version
b12110
Commit
cd959bae9
Binary SHA-256
db82377125f69e87c06b402bba1af072e2a4c4cc9945946e4d6378cc213a84d7
Built from
release
Build flags
None
Backend
CPU
Threads
Not recorded
Interface
http-server
Settings in effect
context_length=4096 parallel=1 speculative=false backend=cpu launch.log_verbosity=4 launch.log_colors=off launch.cache_prompt=false launch.cache_ram_mib=0 launch.cache_reuse=0 launch.continuous_batching=false launch.context_shift=false launch.flash_attn=on launch.cache_type_k=f16 launch.cache_type_v=f16 launch.gpu_layers=0 launch.load_mode=mmap offloaded_layers=0 launch.mmap=true n_batch=2048 n_ubatch=512 n_threads=8 n_threads_batch=8 flash_attn=enabled

Model and weights

Base model
LFM2.5 1.2B Instruct (LFM2.5, 1.2B)
Upstream
LiquidAI/LFM2.5-1.2B-Instruct@b9d816ab510f9a28dca37cb182e9da8b0226e13c
Weights
LiquidAI/LFM2.5-1.2B-Instruct-GGUF@8ed288026e23958ad9dfa92d53ed773a8eee7125
Format
gguf
File 1
LFM2.5-1.2B-Instruct-Q8_0.gguf · 1.16 GiB · sha256 f6b981dcb86917fa463f78a362320bd5e2dc45445df147287eedb85e5a30d26a
File 2
README.md · 3,544 bytes · sha256 f89d69dd107c19936b98ff981456302bc59255cce34b216ecc489d7bafa782e9
Quantization
Q8_0 (8-bit)
Weight bits
8
Group size
32
KV cache
f16
Conversion
Published upstream by LiquidAI
Conversion command
Not recorded

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
37.8 °C, nominal
Thermal at end
37.8 °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, 00:36 UTC
Harness
xybrid-bench 0.4.0 (4c16c5d155dbb45dbce6feedb343009b9d9d173e)
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
Passed · sha256 d486dfbd5fb578340bccbdd0a662527eab38550648d5f44517e5ac71b8824703
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
12/12 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-oneplus13-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