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

Experiment Complete Published

llama.cpp b12110 on Pixel 8 · 8 GB, CPU

LFM2.5 1.2B Instruct as Q8_0 (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 01:01 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-pixel8-lfm2.5-1.2b-8-bit-llama-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 better12.9 12.4–13.3 12.9 ± 0.3 12.8–13.0
Time to first token ms, lower is better24,421 23,107–28,048 24,913 ± 2,071 23,167–26,152
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better84.1 73.1–88.7 82.8 ± 6.7 78.4–88.5

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
123,10788.72,048 tok in 23,080 ms, engine12.4127 tok in 10,232 ms, enginenot recorded36.7 °C, nominal → 38.3 °C, nominal
228,04873.12,048 tok in 28,023 ms, engine12.8127 tok in 9,958 ms, enginenot recorded36.4 °C, nominal → 38.6 °C, nominal
326,34677.82,048 tok in 26,321 ms, engine12.9127 tok in 9,826 ms, enginenot recorded36.6 °C, nominal → 39.0 °C, nominal
425,57180.22,048 tok in 25,544 ms, engine13.0127 tok in 9,778 ms, enginenot recorded36.5 °C, nominal → 38.7 °C, nominal
523,27288.12,048 tok in 23,245 ms, engine12.9127 tok in 9,859 ms, enginenot recorded36.4 °C, nominal → 38.7 °C, nominal
623,13288.62,048 tok in 23,105 ms, engine13.3127 tok in 9,536 ms, enginenot recorded36.4 °C, nominal → 38.4 °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
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
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=9 n_threads_batch=9 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 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
34.3 °C, nominal
Thermal at end
38.4 °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, 01:01 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
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-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