Experiment Complete Published
ExecuTorch 1.6.0 on Pixel 8 · 8 GB, CPU
LFM2.5 350M as 8da4w (4-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 06:09 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: Its output check failed: 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.
Experiment id s4-pixel8-lfm2.5-350m-4-bit-et-xnnpack-2048
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 | 53.0 | 52.7–53.7 | 53.1 ± 0.4 | 52.8–53.3 |
| Time to first token ms, lower is better | Not measured | |||
| Peak memory GiB, lower is better | Not measured | |||
| Prefill speed tok/s, higher is better | 665.9 | 631.1–675.7 | 661.5 ± 16.5 | 658.2–672.7 |
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 | not recorded | 631.12,048 tok in 3,245 ms, engine | 52.7127 tok in 2,408 ms, engine | not recorded | 29.6 °C, nominal → 31.3 °C, nominal | |
| 2 | not recorded | 666.92,048 tok in 3,071 ms, engine | 53.1127 tok in 2,392 ms, engine | not recorded | 28.0 °C, nominal → 30.6 °C, nominal | |
| 3 | not recorded | 656.02,048 tok in 3,122 ms, engine | 53.4127 tok in 2,380 ms, engine | not recorded | 28.3 °C, nominal → 30.8 °C, nominal | |
| 4 | not recorded | 664.92,048 tok in 3,080 ms, engine | 52.8127 tok in 2,404 ms, engine | not recorded | 28.7 °C, nominal → 31.2 °C, nominal | |
| 5 | not recorded | 675.72,048 tok in 3,031 ms, engine | 52.7127 tok in 2,412 ms, engine | not recorded | 29.0 °C, nominal → 31.4 °C, nominal | |
| 6 | not recorded | 674.62,048 tok in 3,036 ms, engine | 53.7127 tok in 2,363 ms, engine | not recorded | 29.2 °C, nominal → 31.7 °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
- ExecuTorch
- Maintainer
- PyTorch (Meta)
- License
- BSD-3-Clause, open source
- Version
- 1.6.0
- Commit
- 4776f71b6f0daa5dfc7d758d5836fc1cc0d40154
- Binary SHA-256
- a214c779c6d098e58572ee7c3c22494afc81a5ad50cbc0fd68d1049f3d872b5a
- Built from
- source
- Build flags
- None
- Backend
- CPU
- Threads
- Not recorded
- Interface
- cli
- Settings in effect
- backend=cpu recipe=lfm2.5-350m-et-xnnpack-8da4w,lfm2_xnnpack_q8da4w.yaml,lfm2.5-350m-et-xnnpack-8da4w.pte runner=xybrid_et_runner process=one per generation echo=false temperature=0 num_bos=0 num_eos=0 reset_before_generation=true eos_ignorable=false threads=engine default (performance cores)
Model and weights
- Base model
- LFM2.5 350M (LFM2.5, 350M)
- Upstream
- LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
- Weights
- LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
- Format
- pte
- File 1
- lfm2.5-350m-et-xnnpack-8da4w.pte · 434.9 MiB · sha256 9742351692899c943bf1016142451cd048ead5031b5bea0d3b4ad54b355cdecd
- File 2
- tokenizer.json · 4.5 MiB · sha256 df1d8d5ec5d091b460562ffd545e4a5e91d17d4a0db7ebe733be34ed374377bd
- Quantization
- 8da4w (4-bit)
- Weight bits
- 4
- Group size
- Not recorded
- KV cache
- fp32
- Conversion
- Converted by Xybrid with executorch export_llm 1.6.0
- Conversion command
- cd "$ROOT/engines/executorch/build/lfm2.5-350m-et-xnnpack-8da4w" && PYTHONPATH="$ROOT/engines/executorch/.venv/lib/python3.12/site-packages/executorch" "$ROOT/engines/executorch/.venv/bin/python" -m executorch.extension.llm.export.export_llm --config "$ROOT/engines/executorch/.venv/lib/python3.12/site-packages/executorch/examples/models/lfm2/config/lfm2_xnnpack_q8da4w.yaml" +base.model_class=lfm2_5_350m "+base.checkpoint=$ROOT/engines/executorch/build/lfm2.5-350m-canonical.pth" "+base.params=$ROOT/downloads/executorch/4776f71b6f0daa5dfc7d758d5836fc1cc0d40154/examples/models/lfm2/config/lfm2_5_350m_config.json" +export.max_seq_length=4096 +export.max_context_length=4096 +export.output_name=lfm2.5-350m-et-xnnpack-8da4w.pte
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
- 26.6 °C, nominal
- Thermal at end
- 31.7 °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, 06:09 UTC
- Harness
- xybrid-bench 0.4.0 (dd753a4204a376082f5252625473323d0771dc20)
- 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
- 7
- Check arithmetic
- Failed · sha256 e629fa6598d732768f7c726b4b621285f9c3b85303900aa912017db7617d8bdb
- Check capital
- Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
- Check opposite
- Failed · sha256 0b0fd31e2478cff0d3c5bf526a0f8f1c780abfb435eec0a8f2c9beed0eaa6bc4
- Check weekday
- Passed · sha256 7d8af1de1262f150187d5938bf649d6c35726970685f916d1ec6392a801b9762
- Check color
- Failed · sha256 ec7d56a01607001e6401366417c5e2eb00ffa0df17ca1a9a831e0b32c8f11bf7
- Check sort
- Failed · sha256 0ca7eabde70df147ffea0ec2627afd6c362a0bfc80b48981b8880485cca2360e
- Check animal
- Failed · sha256 d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35
- Check word
- Failed · sha256 f61e68691bdd0f5ebd3252de0396569d624bd2fba240d66fae90edb456a9f48f
- Check copy
- Passed · sha256 d61e6890d0e3571b0c7693612d41f8d059a1fcdef4ba959c0af4144541d41907
- Check needle-start
- Passed · sha256 8b9af2e5b8b4cfddb87d171997b95c471f8d68a68e30fb5177abeb3332372edd
- Check needle-end
- Passed · sha256 e6589c736af32f81bf239c5eda6de41959122ccc1d05463b75e0eb0c70fc831c
- Check continuation-128
- Passed · sha256 46e2ace9e836d0de7961085acc08170024e02dee11c4040d0a28e45dade9f606
- Detail
- 5/8 of the checks the model passes at BF16; needs 7 and the mandatory ones (needle-start, needle-end). Left out, failed by every BF16 configuration: arithmetic, sort, word, continuation-128.
Reproduce it
pnpm bench run --plan plans/s4-pixel8-lfm2.5-350m-4-bit-et.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 e99d3bf102aa…