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

Commands
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