Skip to content
Stability AI logo

Run StableLM 2 Zephyr 1.6B on iPhone & iPad

General instruction assistant from StableLM 3B outperforming 10x larger models

StableLM 2 Zephyr 1.6B runs 100% private on iPhone & iPad inside Private LLM — no internet connection required, no data sent to any server.

1.6BiPhoneiPadgeneral

Model on Hugging Face

Specifications

Parameters
1.6B
Context window
4K tokens
License
Other
Family
StableLM 3B

What StableLM 2 Zephyr 1.6B is good at

StableLM 2 Zephyr 1.6B scores 5.42 on the MT-Bench benchmark, outperforming several models ten times its size. It is an instruction-tuned language assistant from the StableLM 3B family, built for chat with 1.6 billion parameters and a 4096-token context window. The model is notably good at following user instructions accurately while remaining computationally lightweight.

Which of your devices can run it

iPhone

iPhone 17 Pro MaxiPhone 17 ProiPhone AiriPhone 17iPhone 16 Pro / 16 Pro MaxiPhone 16 / 16 PlusiPhone 16eiPhone 15 Pro / 15 Pro MaxiPhone 15 / 15 PlusiPhone 14 / 14 Plus / 14 Pro / 14 Pro MaxiPhone 13 Pro / 13 Pro MaxiPhone 13 / 13 miniiPhone SE (3rd gen)iPhone 12 Pro / 12 Pro MaxiPhone 12 / 12 miniiPhone 11 / 11 Pro / 11 Pro MaxiPhone XS / XS Max

iPad

iPad Pro (M5, 16GB)iPad Pro (M5, 12GB)iPad Pro (M4, 16GB)iPad Pro (M4, 8GB)iPad Pro (M2, 16GB)iPad Pro (M2, 8GB)iPad Pro (M1, 16GB)iPad Pro (M1, 8GB)iPad Air (M4)iPad Air (M3)iPad Air (M2)iPad Air (M1)iPad Air (4th gen)iPad mini (A17 Pro)iPad mini (6th gen)iPad (A16)iPad (10th gen)

Browse every model that fits iPhone or Mac.

How to run StableLM 2 Zephyr 1.6B in Private LLM

  1. Download Private LLM from the App Store.
  2. Open the in-app model library and choose StableLM 2 Zephyr 1.6B.
  3. Download the model once, then chat fully offline.
Download Private LLM on the App StoreJoin our Discord

Variants & related models

Stability AI logo

Nous Capybara 3B V1.9

2.8B

Complex summaries of advanced topics from an instruction-tuned StableLM 3B assistant

4K contextiPhone & iPad
Stability AI logo

Rocket 3B

2.8B

Detailed general assistant finetuned from StableLM 3B with DPO

4K contextiPhone & iPad
Stability AI logo

StableLM Zephyr 3B

2.8B

General instruction-following assistant fine-tuned from StableLM 3B with DPO

4K contextMac
Meta logo

Airoboros l2 7b 3.0

6.7B

Instruction following specialist built on Llama 2 7B

4K contextiPhone & iPad · Mac
Mistral logo

Airoboros M 7B

7.2B

General instruction-following model built on Mistral with structured math output

33K contextMac
Meta logo

Cat Llama 3 70B Instruct

70.6B

Immersive roleplay via strict prompt adherence, Llama 3 70B finetune

8K contextMac

Frequently asked questions

  • Yes. StableLM 2 Zephyr 1.6B runs on iPhone models with enough memory, such as iPhone 17 Pro Max, iPhone 17 Pro, iPhone Air, iPhone 17, iPhone 16 Pro / 16 Pro Max, iPhone 16 / 16 Plus, iPhone 16e, iPhone 15 Pro / 15 Pro Max, iPhone 15 / 15 Plus, iPhone 14 / 14 Plus / 14 Pro / 14 Pro Max, iPhone 13 Pro / 13 Pro Max, iPhone 13 / 13 mini, iPhone SE (3rd gen), iPhone 12 Pro / 12 Pro Max, iPhone 12 / 12 mini, iPhone 11 / 11 Pro / 11 Pro Max, iPhone XS / XS Max, fully on-device in Private LLM — no internet connection required.

  • StableLM 2 Zephyr 1.6B runs on iPhone and iPad in Private LLM; a Mac is not required.

  • Yes. Once downloaded in Private LLM, StableLM 2 Zephyr 1.6B runs 100% on-device — no internet connection, and nothing is sent to any server.

  • Private LLM is a one-time purchase with no subscription and no per-message cost. The models themselves are open source — once downloaded, they run offline with nothing to pay per use.

Why run StableLM 2 Zephyr 1.6B in Private LLM

Private LLM has run local AI on iPhone, iPad, and Mac since 2023, well before Apple Intelligence, LM Studio, Ollama, etc. existed. Inference happens on your device, so your StableLM 2 Zephyr 1.6B conversations never reach a server.

Specifications and summary come from StableLM 2 Zephyr 1.6B's Hugging Face model card. Private LLM ships its own model builds and isn't affiliated with the model's authors.