iPhone / iPad · 2023 · A16
Local AI on the iPhone 15
Most common 2023 iPhone. Qwen 3 1.7B and Llama 3.2 1B are the reliable in-app picks.
- Advertised RAM
- 6 GB
- Usable for a model
- ~2.6 GB
- Compute
- Metal / ANE
- LM Mini path
- MLX / Metal
Start in LM Mini
Install the app, pick one of these, chat offline.
Best everyday phone pick for most people — chat, tools, and general help.
DeepSeek R1 Distill 1.5B Fits · ~1.0–1.1 GBA mini “thinking” model — stronger at math and step-by-step reasoning.
Gemma 3 1B Instruct Fits · ~700–750 MBGoogle’s smallest Gemma 3 chat model. Great starter for everyday questions.
Llama 3.2 1B Instruct Fits · ~700–808 MBMeta’s pocket Llama — fast, tool-friendly, and solid for light chat.
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.
| Model | Params | Q4 | Here | Where |
|---|---|---|---|---|
| Qwen 3 0.6B | 0.6B | ~400–500 MB | Runs well | In LM Mini |
| Gemma 3 1B Instruct | 1B | ~700–750 MB | Fits | In LM Mini |
| Llama 3.2 1B Instruct | 1B | ~700–808 MB | Fits | In LM Mini |
| DeepSeek R1 Distill 1.5B | 1.5B | ~1.0–1.1 GB | Fits | In LM Mini |
| Qwen 3 1.7B | 1.7B | ~1.1–1.2 GB | Fits | In LM Mini |
| Qwen 3.5 0.8B | 0.8B | ~500–600 MB | Fits | Studio / Ollama |
| SmolLM2 1.7B Instruct | 1.7B | ~1.0 GB | Fits | Studio / Ollama |
| Qwen 2.5 1.5B Instruct | 1.5B | ~1.0 GB | Fits | Studio / Ollama |
| Qwen 3.5 2B | 2B | ~1.3–1.5 GB | Tight | Studio / Ollama |
| Gemma 3n E2B | 2B | ~1.5 GB | Tight | Studio / Ollama |
| Gemma 4 E2B Instruct | 2.3B | ~1.4–1.8 GB (Q4/QAT) | Tight | Studio / Ollama |
Too big for this phone
Host these on LM Studio or Ollama, then chat from iPhone 15.
- Llama 3.2 3B Instruct — PC + Connect
- Phi-4 Mini Instruct — PC + Connect
- Qwen 3 4B Instruct 2507 — PC + Connect
- Gemma 3 4B Instruct — PC + Connect
- Qwen 3 8B — PC + Connect
- Gemma 3 12B Instruct — PC + Connect
How we score this
iPhone 15 ships with 6 GB. After iPhone / iPad we budget ~2.6 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.