LFM2.5 2.6B on iPhone 12 · 4 GB
Experiment Unsupported Published
llama.cpp b12110 on iPhone 12 · 4 GB, Metal
LFM2.5 2.6B as Q8_0 (8-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 14:44 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: llama.cpp errored on the arithmetic check in qualification: The app failed: llama_decode(token 1) returned -3
Experiment id s4-iphone12-lfm2.5-2.6b-8-bit-llama-256
Unsupported configuration
llama.cpp errored on the arithmetic check in qualification: The app failed: llama_decode(token 1) returned -3
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
- llama.cpp
- Maintainer
- ggml-org
- License
- MIT, open source
- Version
- b12110
- Commit
- cd959bae99ff4bed22bef2604f45241c09bbb8c8
- Binary SHA-256
- c1a1252fac9adcbcd54d3ce0f381dba44f6ba05f0561d4b05e79a04228a8ea12
- Built from
- release
- Build flags
- None
- Backend
- Metal
- Threads
- Not recorded
- Interface
- ios-app
- Settings in effect
- gpu_layers=999 flash_attn=on cache_type_k=f16 cache_type_v=f16 mmap=true
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 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
- 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, 14:44 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…