[Models](/models) / [Families](/models/family) / Llama 3 70B

# Local Llama 3 70B Models for Mac

Run Llama 3 70B models fully offline on Mac inside Private LLM — private, with nothing sent to a server.

4 models

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

### Cat Llama 3 70B Instruct

70.6B

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

8K contextMac

[View details →](/models/cat-llama-3-70b-instruct)

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

### Meta Llama 3 70B Instruct

70.6B

General-purpose model in the Llama 3 70B family

Mac

[View details →](/models/meta-llama-3-70b)

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

### Smaug Llama 3 70B Instruct

70.6B

General conversationalist fine-tuned from Llama 3 70B, matching GPT-4 Turbo dialogue

8K contextMac

[View details →](/models/smaug-llama-3-70b-instruct)

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

### Smaug Llama 3 70B Instruct Abliterated v3

70.6B

Uncensored abliterated Llama 3 70B retaining original knowledge

8K contextMac

[View details →](/models/smaug-llama-3-70b-instruct-abliterated-v3)

[Browse all models→](/models)

## Frequently asked questions

-   What are the best Llama 3 70B models to run locally on Mac?
    
    Private LLM runs Llama 3 70B models on Mac, fully on-device. Larger variants like Cat Llama 3 70B Instruct, Meta Llama 3 70B Instruct, Smaug Llama 3 70B Instruct need more memory, so the right pick depends on your device's RAM.
    
-   Are Llama 3 70B models private in Private LLM?
    
    Yes. Every Llama 3 70B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
    
-   Do Llama 3 70B models work offline?
    
    Only the one-time download needs a connection. After that, every Llama 3 70B model runs 100% offline in Private LLM.