[Models](/models) / [Families](/models/family) / Llama 2 7B

# Local Llama 2 7B Models for iPhone, iPad & Mac

Run Llama 2 7B models fully offline on iPhone, iPad & Mac inside Private LLM — private, with nothing sent to a server.

3 models

![Meta logo](/model-logos/meta.svg)

### Spicyboros 7b 2.2

7B

Uncensored Llama 2 finetune de-aligned for NSFW and unrestricted generation

4K contextiPhone & iPad · Mac

[View details →](/models/spicyboros-7b-2.2)

![Meta logo](/model-logos/meta.svg)

### Xwin LM 7B v0.1

7B

General assistant finetune of Llama 2 7B, top AlpacaEval win rate

4K contextMac

[View details →](/models/xwin-lm-7b-v0.1)

![Meta logo](/model-logos/meta.svg)

### Airoboros l2 7b 3.0

6.7B

Instruction following specialist built on Llama 2 7B

4K contextiPhone & iPad · Mac

[View details →](/models/airoboros-l2-7b-3.0)

[Browse all models→](/models)

## Frequently asked questions

-   What are the best Llama 2 7B models to run locally on iPhone, iPad & Mac?
    
    Private LLM runs Llama 2 7B models on iPhone, iPad & Mac, fully on-device. Larger variants like Spicyboros 7b 2.2, Xwin LM 7B v0.1, Airoboros l2 7b 3.0 need more memory, so the right pick depends on your device's RAM.
    
-   Are Llama 2 7B models private in Private LLM?
    
    Yes. Every Llama 2 7B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
    
-   Do Llama 2 7B models work offline?
    
    Only the one-time download needs a connection. After that, every Llama 2 7B model runs 100% offline in Private LLM.