Experiment Complete Published
llama.cpp b12110 on OnePlus 13 · 16 GB, CPU
LFM2.5 2.6B as Q4_K_M (4-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 02:45 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: Its output check failed: 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.
Experiment id s4-oneplus13-lfm2.5-2.6b-4-bit-llama-256
Summary
Over 6 valid trials of 6 attempted (6 planned), computed from the raw trials below.
| Metric | Median | Range | Mean ± SD | Quartiles |
|---|---|---|---|---|
| Decode speed tok/s, higher is better | 28.3 | 26.9–29.2 | 28.2 ± 1.1 | 27.2–29.1 |
| Time to first token ms, lower is better | 2,025 | 1,876–2,206 | 2,031 ± 166 | 1,881–2,174 |
| Peak memory GiB, lower is better | Not measured | |||
| Prefill speed tok/s, higher is better | 127.4 | 116.5–137.0 | 127.2 ± 10.4 | 118.2–136.8 |
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.
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.
| Trial | Time to first token ms | Prefill tok/s | Decode tok/s | Peak memory GiB | Thermal | Note |
|---|---|---|---|---|---|---|
| 1 | 2,177 | 118.1256 tok in 2,168 ms, engine | 27.1127 tok in 4,693 ms, engine | not recorded | 40.9 °C, nominal → 42.3 °C, nominal | |
| 2 | 1,879 | 137.0256 tok in 1,869 ms, engine | 29.2127 tok in 4,352 ms, engine | not recorded | 41.1 °C, nominal → 43.4 °C, nominal | |
| 3 | 2,206 | 116.5256 tok in 2,198 ms, engine | 27.7127 tok in 4,584 ms, engine | not recorded | 40.8 °C, nominal → 42.8 °C, nominal | |
| 4 | 1,885 | 136.2256 tok in 1,879 ms, engine | 29.0127 tok in 4,381 ms, engine | not recorded | 40.7 °C, nominal → 43.1 °C, nominal | |
| 5 | 2,164 | 118.6256 tok in 2,158 ms, engine | 26.9127 tok in 4,714 ms, engine | not recorded | 40.6 °C, nominal → 42.7 °C, nominal | |
| 6 | 1,876 | 137.0256 tok in 1,869 ms, engine | 29.2127 tok in 4,352 ms, engine | not recorded | 40.7 °C, nominal → 43.0 °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-Q4_K_M.gguf · 1.56 GiB · sha256 02a8b7e17487d326e46d68ce0ba24211e1b80a14c4cd0597fa73c1cd697f52ed
- File 2
- README.md · 3,068 bytes · sha256 d08b79260b3998e96792777085e4175b730667568f3a953ad4ac9099cfa27056
- Quantization
- Q4_K_M (4-bit)
- Weight bits
- 4
- Group size
- Not recorded
- 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
- 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
- 41.3 °C, nominal
- Thermal at end
- 43.3 °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, 02:45 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
- Failed
- 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 7a3bb1905f2039638dff3f8a3da57abf7b1da32596b04c5ed04c5296f155196a
- Check opposite
- Passed · sha256 69a13e1ba8e284fcc26068ec8aa80e8a7e7f8bbebe86dc7a45424411198a6859
- Check weekday
- Passed · sha256 03db656ee680fb1053be9c98631722488bb10269075159dbae5b000f0359dae2
- Check color
- Failed · sha256 a4849893c59e4aa15ff645cadd4cce0fbd882097352a75d8e6f23619578a73c6
- Check sort
- Failed · sha256 9323cbae61cd372adbe47d7bb1dfc5d32311d26031ec082dd1987508e08e986c
- Check animal
- Passed · sha256 3e9114b6df29561433c18b3a6abce2c635fbd8e9ff25b5fcee93149bfea52859
- Check word
- Passed · sha256 d1bf31457072aaa4c116ea5819a644456232fdd87b15203d3eafdd5e541f4e61
- Check copy
- Passed · sha256 d8c711dfa5fef68d1d0f86320daeca065b91bc8d0dbcea210f8b9ef80eefc6c2
- Check needle-start
- Passed · sha256 e4b695d890438ad108a6fd9cb2e39bf857a00a883f231741c1f92416c1b218c4
- Check needle-end
- Passed · sha256 34b7b9e17d75628c346994d8be48566a2dd011ba8533dc75fc33a579ee705365
- Check continuation-128
- Failed · sha256 db31f2ddd5a91fd7cd0eda45879b0d50e96ef9636478715e356c0781f7e908b2
- 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
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
- This record, as committed JSON, schema v0.3.0
- Complete finalized session evidence raw ·
sha256 dd947a836adf…