LFM2.5 1.2B Instruct on iPhone 12 · 4 GB
Experiment Unsupported Published
llama.cpp b12110 on iPhone 12 · 4 GB, Metal
LFM2.5 1.2B Instruct as BF16 (bf16), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 13 Nov 2026, 14:30 UTC by Glenn Sonna, Xybrid.
Doesn’t count in rankings: llama.cpp errored on the opposite check in qualification: The app wrote no result for run (exit 1); iOS ends an app that exceeds its memory limit or leaves the foreground.
Experiment id s4-iphone12-lfm2.5-1.2b-bf16-llama-256
Unsupported configuration
llama.cpp errored on the opposite check in qualification: The app wrote no result for run (exit 1); iOS ends an app that exceeds its memory limit or leaves the foreground.
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 1.2B Instruct (LFM2.5, 1.2B)
- Upstream
- LiquidAI/LFM2.5-1.2B-Instruct@b9d816ab510f9a28dca37cb182e9da8b0226e13c
- Weights
- LiquidAI/LFM2.5-1.2B-Instruct-GGUF@8ed288026e23958ad9dfa92d53ed773a8eee7125
- Format
- gguf
- File 1
- LFM2.5-1.2B-Instruct-BF16.gguf · 2.18 GiB · sha256 3d80914b903cd6f3cc041208cf20ec46a3224f840c732e5fd7698832b4743d1b
- File 2
- README.md · 3,544 bytes · sha256 f89d69dd107c19936b98ff981456302bc59255cce34b216ecc489d7bafa782e9
- Quantization
- BF16 (bf16)
- Weight bits
- 16
- 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
- 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
- fair
- 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, 14:30 UTC
- Harness
- xybrid-bench 0.4.0 (b9b5401ab73996ff528d76dbdc3e14ec79576bd0)
- 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-lfm2.5-1.2b-bf16.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 96d03cc2bea6…