LFM2.5 2.6B on iPhone 12 · 4 GB
Experiment Unsupported Published
uzu 0.6.17 on iPhone 12 · 4 GB, Metal
LFM2.5 2.6B as mirai-l (8-bit), archive 2048 input / 128 output: a 2048-token prompt and 128 tokens out. Measured 13 Nov 2026, 14:57 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).
Experiment id s4-iphone12-lfm2.5-2.6b-8-bit-uzu-2048
Unsupported configuration
uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).
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
- e4466cdd3ae2ba882e52ef3d07355e6bd09762660c26d393f8a53b87f53605fc
- Built from
- package
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- ios-app
- Settings in effect
- unsupported=uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).
Model and weights
- Base model
- LFM2.5 2.6B (LFM2.5, 2.6B)
- Upstream
- LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
- Weights
- trymirai/LFM2.5-2.6B-L@626efec9dff23cd26189db75dd9f90250a00c652
- Format
- mirai
- File 1
- README.md · 3,251 bytes · sha256 55c8dc19f11686c7ccfe7b12fb3e41aa0d4c7f0d1740a5be287c650c2e788e69
- File 2
- config.json · 59,891 bytes · sha256 ae659366b2d7c6c4134c919ed29666dfc0b3c8eadcab00c08e162db276b41671
- File 3
- model.safetensors · 2.60 GiB · sha256 a963a14d4ea236e2f46e1051c1ad0d97bcbc7f5af9095f63929e824569aa1c1e
- File 4
- tokenizer.json · 17.1 MiB · sha256 695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
- Quantization
- mirai-l (8-bit)
- Weight bits
- 8
- 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
- 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
- nominal
- Thermal at end
- nominal
- Thermal gate
- iOS thermal state nominal
- Throttling detected
- Not recorded
Provenance
- Measured by
- Glenn Sonna, Xybrid
- Operator affiliation
- Xybrid
- Run at
- 13 Nov 2026, 14:57 UTC
- Harness
- xybrid-bench 0.4.0 (117217d03b2f928faaa3e043fa985c3598eb970e)
- Methodology
- v0.6
- Publication
- published
- Published
- 16 Nov 2026, 10:23 UTC
- Reviewed by
- Glenn Sonna
Output check
- Result
- Not run
- Method
- Not recorded
- Reference
- Not recorded
- Reference SHA-256
- Not recorded
- Required passing checks
- Not recorded
- Detail
- Not recorded
Reproduce it
pnpm bench run --plan plans/s4-iphone12-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
- This record, as committed JSON, schema v0.3.0
- Complete finalized session evidence raw ·
sha256 c7982256c2f9…