Can I run a local LLM on iPhone Air?

Yes, at the right size. iPhone Air has about 6.2 GB usable. Try Qwen 3 4B Instruct 2507, Gemma 3 4B Instruct, Phi-4 Mini Instruct in LM Mini (the free plan includes four 1–1.7B starter models; bigger catalog models need LM Mini Pro). Bigger models belong on a PC via Connect.

How much RAM does iPhone Air really have for AI?

12 GB advertised, ~6.2 GB left for weights + KV cache. That is why 7B Q4 fails on many 8 GB phones.

iPhone / iPad · 2025 · A19

Local AI on the iPhone Air

12 GB in a thin chassis. RAM matches the 17 Pro; thermals do not. 4B is the sweet spot. Long 8B sessions will throttle — Connect is still the 14B path.

Advertised RAM: 12 GB
Usable for a model: ~6.2 GB
Compute: Metal / ANE
LM Mini path: GGUF / Metal (MLX with Pro)

Start in LM Mini

Install the app, pick one of these, chat offline. The free plan includes four small starter models (1–1.7B); models marked Pro need LM Mini Pro.

Qwen 3 4B Instruct 2507 Runs well · ~2.4–2.5 GB · Pro

Balanced daily driver for Pro phones and Macs — quality without a desktop GPU.

Gemma 3 4B Instruct Runs well · ~2.7–3.7 GB · Pro

Google’s mid-size Gemma 3 — sharper answers; some builds can look at images.

Phi-4 Mini Instruct Runs well · ~2.3–2.4 GB · Pro

Strong reasoning in a phone-friendly package — great for explanations and code-ish help.

Llama 3.2 3B Instruct Runs well · ~1.9–2.0 GB · Pro

Noticeably smarter than 1B — good for writing help and longer chats on Pro phones.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

App Store Google Play Mac & more

What actually fits

Q4 weights plus KV cache. “Tight” means close Chrome first.

Model	Params	Q4	Here	Where
Qwen 3 0.6B	0.6B	~400–500 MB	Runs well	In LM Mini · Pro
Gemma 3 1B Instruct	1B	~700–750 MB	Runs well	In LM Mini · Free
Llama 3.2 1B Instruct	1B	~700–808 MB	Runs well	In LM Mini · Free
DeepSeek R1 Distill 1.5B	1.5B	~1.0–1.1 GB	Runs well	In LM Mini · Free
Qwen 3 1.7B	1.7B	~1.1–1.2 GB	Runs well	In LM Mini · Free
Llama 3.2 3B Instruct	3B	~1.9–2.0 GB	Runs well	In LM Mini · Pro
Phi-4 Mini Instruct	3.8B	~2.3–2.4 GB	Runs well	In LM Mini · Pro
Qwen 3 4B Instruct 2507	4B	~2.4–2.5 GB	Runs well	In LM Mini · Pro
Gemma 3 4B Instruct	4B	~2.7–3.7 GB	Runs well	In LM Mini · Pro
Qwen 3.5 0.8B	0.8B	~500–600 MB	Runs well	Studio / Ollama
SmolLM2 1.7B Instruct	1.7B	~1.0 GB	Runs well	Studio / Ollama
Qwen 2.5 1.5B Instruct	1.5B	~1.0 GB	Runs well	Studio / Ollama
Qwen 3.5 2B	2B	~1.3–1.5 GB	Runs well	Studio / Ollama
Gemma 3n E2B	2B	~1.5 GB	Runs well	Studio / Ollama
Gemma 4 E2B Instruct	2.3B	~1.4–1.8 GB (Q4/QAT)	Runs well	Studio / Ollama
Qwen 2.5 3B Instruct	3B	~1.9 GB	Runs well	Studio / Ollama
SmolLM3 3B	3B	~1.9 GB (Q4)	Runs well	Studio / Ollama
Nemotron 3 Nano 4B	4B	~2.5 GB (Q4)	Runs well	Studio / Ollama
Qwen 3.5 4B	4B	~2.5–2.8 GB	Runs well	Studio / Ollama
Gemma 3n E4B	4B	~2.6 GB (Q4)	Runs well	Studio / Ollama
Gemma 4 E4B Instruct	4.5B	~2.6–3.2 GB (Q4/QAT)	Runs well	Studio / Ollama
Mistral 7B Instruct	7B	~4.1 GB (Q4)	Tight	Studio / Ollama
OLMo 3 7B Instruct	7B	~4.3 GB (Q4)	Tight	Studio / Ollama
Qwen 2.5 7B Instruct	7B	~4.4 GB (Q4)	Tight	Studio / Ollama

Too big for this phone

Host these on LM Studio or Ollama, then chat from iPhone Air.

How we score this

iPhone Air ships with 12 GB. After iPhone / iPad we budget ~6.2 GB for inference. A 7B Q4 is ~4.4 GB on disk and wants ~6.5 GB live — that is why it fails on most 8 GB phones. 12–16 GB Android can try 8B. Apple 8 GB phones should live in 1B–4B.