Run LFM2.5 1.2B Instruct locally on iPhone, iPad & Mac

Generalists · 0.73 GB download · needs 2 GB RAM · Q4_K_M GGUF

Smallest & fastest — replaces Llama 3.2 1B, which it beats on every published benchmark (GPQA, MMLU-Pro, IFEval, tool-use) at a smaller file size. 32K context, tool-calling support. LFM Open License v1.0 (same terms as our other LFM2 entries).

In privateSLM, LFM2.5 1.2B Instruct is an everyday assistant for chat, writing, summarising and quick questions. You download the model once, and from then on every conversation runs entirely on your device — no cloud, no account, no tracking, and it keeps working with the radio off.

At a glance

ModelLFM2.5 1.2B Instruct
CategoryGeneralists
Download size0.73 GB (one time)
QuantizationQ4_K_M (GGUF)
Minimum device RAM2 GB
Runs offlineYes — fully on-device after download
SourceHugging Face

Will it run on my device?

LFM2.5 1.2B Instruct needs a device with at least 2 GB of RAM — that means virtually every iPhone, iPad and Mac that can install privateSLM. The privateSLM catalog states the RAM requirement for every model up front, so you know before you download.

How to run LFM2.5 1.2B Instruct in privateSLM

  1. Get privateSLM on the App Store — one-time purchase, no subscription.
  2. Open Models, pick LFM2.5 1.2B Instruct, and tap Download (0.73 GB, once).
  3. Select it as your active model and chat — airplane mode included.

On iPhones, iPads and Macs with Apple Intelligence, privateSLM can also answer instantly with the built-in system model — zero downloads. A catalog model like LFM2.5 1.2B Instruct is for when you want this particular specialist, offline, under your control.

Related models

FAQ

Does LFM2.5 1.2B Instruct run offline on iPhone?

Yes. After a one-time 0.73 GB download inside privateSLM, LFM2.5 1.2B Instruct runs entirely on-device via llama.cpp. Airplane mode works — nothing is ever sent to a server.

How much RAM does LFM2.5 1.2B Instruct need?

A device with at least 2 GB of RAM — in practice virtually every iPhone, iPad and Mac that can install privateSLM.

Is LFM2.5 1.2B Instruct free to use in privateSLM?

The model itself is open-weights (Q4_K_M GGUF) and the download is free. privateSLM is a one-time purchase — no subscription, no per-message fees.