LFM2.5 2.6B on OnePlus 13 · 16 GB

Experiment Complete Published

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

LFM2.5 2.6B as Q8_0 (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 02:01 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-oneplus13-lfm2.5-2.6b-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 better17.9 17.7–18.0 17.9 ± 0.1 17.8–17.9
Time to first token ms, lower is better12,624 12,591–12,634 12,618 ± 18.5 12,604–12,633
Peak memory GiB, lower is betterNot measured
Prefill speed tok/s, higher is better162.4 162.2–162.8 162.4 ± 0.2 162.2–162.6

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
112,591162.82,048 tok in 12,580 ms, engine17.7127 tok in 7,157 ms, enginenot recorded41.0 °C, nominal → 47.6 °C, nominal
212,632162.22,048 tok in 12,623 ms, engine17.9127 tok in 7,087 ms, enginenot recorded40.5 °C, nominal → 47.3 °C, nominal
312,615162.52,048 tok in 12,605 ms, engine18.0127 tok in 7,069 ms, enginenot recorded40.5 °C, nominal → 47.3 °C, nominal
412,634162.22,048 tok in 12,625 ms, engine17.9127 tok in 7,089 ms, enginenot recorded40.5 °C, nominal → 47.3 °C, nominal
512,601162.62,048 tok in 12,592 ms, engine17.9127 tok in 7,093 ms, enginenot recorded40.3 °C, nominal → 47.1 °C, nominal
612,633162.32,048 tok in 12,622 ms, engine17.7127 tok in 7,163 ms, enginenot recorded40.5 °C, nominal → 47.3 °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 2.6B (LFM2.5, 2.6B)
Upstream
LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
Weights
LiquidAI/LFM2.5-2.6B-GGUF@e7caca5d835a3901a8e0d63e94009429bafafdfc
Format
gguf
File 1
LFM2.5-2.6B-Q8_0.gguf · 2.68 GiB · sha256 1e22128dfa128bdfb684da167e74e072d0a056baa7d06d9f280291e2839b0fc9
File 2
README.md · 3,068 bytes · sha256 d08b79260b3998e96792777085e4175b730667568f3a953ad4ac9099cfa27056
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
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
37.7 °C, nominal
Thermal at end
47.4 °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, 02:01 UTC
Harness
xybrid-bench 0.4.0 (06e6e2044fde4c9ac013e3857bc95aa939259704)
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 68ce25cb2c4b530f85434cd352428b022149c641163300e566f4f9ee9d789bcf
Check capital
Passed · sha256 b1098d691672b55e98767ac84c6d8375f7bcc0d78154c861ea70ac2ff66e0ba7
Check opposite
Passed · sha256 7c90b06eef25984adf77ec226311829bbc1065a033e9ad6b26d9bd0dfdc65f95
Check weekday
Passed · sha256 03db656ee680fb1053be9c98631722488bb10269075159dbae5b000f0359dae2
Check color
Failed · sha256 a4849893c59e4aa15ff645cadd4cce0fbd882097352a75d8e6f23619578a73c6
Check sort
Failed · sha256 6904619ddb316a20bc1220a9088da9a4181f1f16766b6fdd188defd9cddc4c75
Check animal
Passed · sha256 3e9114b6df29561433c18b3a6abce2c635fbd8e9ff25b5fcee93149bfea52859
Check word
Passed · sha256 d1bf31457072aaa4c116ea5819a644456232fdd87b15203d3eafdd5e541f4e61
Check copy
Passed · sha256 d8c711dfa5fef68d1d0f86320daeca065b91bc8d0dbcea210f8b9ef80eefc6c2
Check needle-start
Passed · sha256 56a69645d0ff053b3b7001c224f07a374bf963a22c9fa4706dda5e56e3616870
Check needle-end
Passed · sha256 34b7b9e17d75628c346994d8be48566a2dd011ba8533dc75fc33a579ee705365
Check continuation-128
Passed · sha256 35b435d7f1c75bb05c07d58cad000525a1d62d6dbe7fd00ae7416953dfa26286
Detail
9/9 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-8-bit.json

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

Raw data