iPhone / iPad · 2024 · A18 Pro

Local AI on the iPhone 16 Pro

Same 8 GB and A18 Pro as the Max. Local AI feels snappy on 1.7B–4B; leave 8B for a Mac or Connect.

Advertised RAM
8 GB
Usable for a model
~3.6 GB
Compute
Metal / ANE
LM Mini path
MLX / Metal

Start in LM Mini

Install the app, pick one of these, chat offline.

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

What actually fits

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

ModelParamsQ4HereWhere
Qwen 3 0.6B 0.6B ~400–500 MB Runs well In LM Mini
Gemma 3 1B Instruct 1B ~700–750 MB Runs well In LM Mini
Llama 3.2 1B Instruct 1B ~700–808 MB Runs well In LM Mini
DeepSeek R1 Distill 1.5B 1.5B ~1.0–1.1 GB Runs well In LM Mini
Qwen 3 1.7B 1.7B ~1.1–1.2 GB Runs well In LM Mini
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
Llama 3.2 3B Instruct 3B ~1.9–2.0 GB Fits In LM Mini
Phi-4 Mini Instruct 3.8B ~2.3–2.4 GB Fits In LM Mini
Qwen 3.5 2B 2B ~1.3–1.5 GB Fits Studio / Ollama
Gemma 3n E2B 2B ~1.5 GB Fits Studio / Ollama
Gemma 4 E2B Instruct 2.3B ~1.4–1.8 GB (Q4/QAT) Fits Studio / Ollama
Qwen 2.5 3B Instruct 3B ~1.9 GB Fits Studio / Ollama
SmolLM3 3B 3B ~1.9 GB (Q4) Fits Studio / Ollama
Qwen 3 4B Instruct 2507 4B ~2.4–2.5 GB Tight In LM Mini
Nemotron 3 Nano 4B 4B ~2.5 GB (Q4) Tight Studio / Ollama
Qwen 3.5 4B 4B ~2.5–2.8 GB Tight Studio / Ollama
Gemma 3n E4B 4B ~2.6 GB (Q4) Tight Studio / Ollama

Too big for this phone

Host these on LM Studio or Ollama, then chat from iPhone 16 Pro.

How we score this

iPhone 16 Pro ships with 8 GB. After iPhone / iPad we budget ~3.6 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.