Experiment Failed Published
uzu 0.6.17 on iPhone 12 · 4 GB, Metal
LFM2.5 350M as mirai-m (4-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 02:31 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: No trial was valid.
Experiment id s4-iphone12-lfm2.5-350m-4-bit-uzu-2048
Errors
- trial: No trial was valid.
- trial: No trial was valid.
- trial: No trial was valid.
- trial: No trial was valid.
- trial: No trial was valid.
- trial: No trial was valid.
Summary
Over 0 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 | Not measured | |||
| 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 | Not measured | |||
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 |
|---|---|---|---|---|---|---|
| 1Invalid | 2,405 | 884.32,048 tok in 2,316 ms, engine | 112.6107 tok in 950 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
| 2Invalid | 2,418 | 885.12,048 tok in 2,314 ms, engine | 107.8107 tok in 993 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
| 3Invalid | 2,399 | 886.62,048 tok in 2,310 ms, engine | 112.8107 tok in 948 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
| 4Invalid | 2,407 | 884.42,048 tok in 2,316 ms, engine | 112.7107 tok in 950 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
| 5Invalid | 2,401 | 882.82,048 tok in 2,320 ms, engine | 114.1107 tok in 938 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
| 6Invalid | 2,371 | 886.72,048 tok in 2,310 ms, engine | 114.3107 tok in 936 ms, engine | not recorded | nominal → nominal | Generated 108 tokens, not 128. |
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
- Apple iPhone13,2
- Cohort
- iPhones (mobile)
- SoC
- Apple A14 Bionic
- CPU
- 6-core CPU (2 performance, 4 efficiency)
- GPU
- 4-core Apple GPU
- NPU
- 16-core Neural Engine
- RAM
- 4.00 GiB
- OS
- iOS 27.2.1 (24B156)
- Kernel
- Darwin Kernel Version 27.2.0: Tue Oct 13 21:44:36 PDT 2026; root:xnu-13432.42.3~28/RELEASE_ARM64_T8101
- Power
- usb
- Low power mode
- No
- App state
- active
Engine
- Engine
- uzu
- Maintainer
- Mirai
- License
- MIT, open source
- Version
- 0.6.17
- Commit
- Not recorded
- Binary SHA-256
- c2ad72f6c7e394f758cbc77dc71c868a9c3d52371bc1379a9e49e3940bc22586
- Built from
- package
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- ios-app
- Settings in effect
- backend=metal app=XybridBench process=one app launch per generation threads=engine default session=new per generation sampling=greedy prompt=user content of the frozen chat envelope uzu_identifier=liquidai:lfm2.5:350m:mirai:mirai-m:4
Model and weights
- Base model
- LFM2.5 350M (LFM2.5, 350M)
- Upstream
- LiquidAI/LFM2.5-350M@9921cd4d82c0e3986887aa4b376f9446729ef8a3
- Weights
- trymirai/LFM2.5-350M-M@1023c49cfc41338ff513b2359a4fe8626fe4e6c7
- Format
- mirai
- File 1
- README.md · 3,306 bytes · sha256 fa2aac1b60ca223ab0761e052263ac98687b13a999325f7131f125d68b5f874b
- File 2
- config.json · 37,022 bytes · sha256 e9f941c136b12c2e1b848d8266f1e94c0a547ce61ec130013cdbb18447a375a7
- File 3
- model.safetensors · 183.9 MiB · sha256 984b8e9e7e47d943f027ea83df4ba52d303f2ab42e118512c243438ba1a6f74a
- File 4
- tokenizer.json · 4.5 MiB · sha256 df1d8d5ec5d091b460562ffd545e4a5e91d17d4a0db7ebe733be34ed374377bd
- Quantization
- mirai-m (4-bit)
- Weight bits
- 4
- Group size
- Not recorded
- KV cache
- uzu default
- Conversion
- Published upstream by trymirai
- 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
- nominal
- Thermal at end
- nominal
- Thermal gate
- iOS thermal state nominal
- Throttling detected
- No
Provenance
- Measured by
- Glenn Sonna, Xybrid
- Operator affiliation
- Xybrid
- Run at
- 13 Nov 2026, 02:31 UTC
- Harness
- xybrid-bench 0.4.0 (8130262155c269b3ee57ab53b9fb646fd29790c2)
- 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
- 7
- Check arithmetic
- Failed · sha256 4a44dc15364204a80fe80e9039455cc1608281820fe2b24f1e5233ade6af1dd5
- Check capital
- Passed · sha256 5dd272b4f316b776a7b8e3d0894b37e1e42be3d5d3b204b8a5836cc50597a6b1
- Check opposite
- Passed · sha256 f151cd9e12c8994edfa316e4624f956bc68460454869177f287146f8cc956a12
- Check weekday
- Passed · sha256 7d8af1de1262f150187d5938bf649d6c35726970685f916d1ec6392a801b9762
- Check color
- Passed · sha256 d486dfbd5fb578340bccbdd0a662527eab38550648d5f44517e5ac71b8824703
- Check sort
- Failed · sha256 edb794d615a63f5eec436d83bed7299d6af36f508c0bf38a3c1cd85d6e4ebd56
- Check animal
- Passed · sha256 4b227777d4dd1fc61c6f884f48641d02b4d121d3fd328cb08b5531fcacdabf8a
- 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
- Failed · sha256 5dc99dc1de83d6b0ff37b91fff7ca5b0c1ae5493c987f0dadd9d5db7ae6923d5
- Detail
- 8/8 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-iphone12-lfm2.5-350m-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 ac1a231e5df2…