Best models for iPhone & iPad
Recent A17/A18/M-series with 8 GB+ unified memory
Sub-3 B parameter models that ship with our iOS app and run entirely on-device. No internet, no API keys — just inference.
- 1
HuggingFace
SmolLM2 360M
Compact 360M model. Good for basic tasks on very constrained devices.
0.36B≥ 0.75 GB - 2
HuggingFace
SmolLM2 1.7B
Capable 1.7B model from HuggingFace. Good balance for mobile devices.
1.7B≥ 1.48 GB - 3
Meta
Llama 3.2 1B Instruct
Ultra-compact 1B model. Runs on virtually any device including smartphones.
1.24B≥ 1.25 GB - 4
Meta
Llama 3.2 3B Instruct
Meta's compact 3B model designed for edge and mobile deployment.
3.2B≥ 2.38 GB - 5
Alibaba
Qwen 2.5 1.5B
Compact 1.5B model with strong multilingual and coding abilities.
1.5B≥ 1.54 GB - 6
Alibaba
Qwen 2.5 3B
Versatile 3B model with strong reasoning and multilingual capabilities.
3B≥ 2.46 GB - 7
Google
Gemma 3 1B
Google's latest tiny 1B model. Excellent quality for its size.
1B≥ 1.25 GB - 8
Microsoft
Phi-3.5 Mini 3.8B
Tiny but capable 3.8B model. Runs on almost any hardware including phones.
3.8B≥ 2.73 GB
Not sure which fits your machine? Auto-detect your hardware →