[Models](/models) / [Families](/models/family) / Llama 2 13B

# Local Llama 2 13B Models for Mac

Run Llama 2 13B models fully offline on Mac inside Private LLM — private, with nothing sent to a server.

5 models

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

### Mythomax L2 13B

13B

Roleplay specialist merging Llama 2 understanding and writing models

4K contextMac

[View details →](/models/mythomax-l2-13b)

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

### Spicyboros 13B

13B

Uncensored de-alignment finetune of Llama 2 13B for unrestricted tasks

4K contextMac

[View details →](/models/spicyboros-13b-2.2)

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

### Synthia 13B 1.2

13B

General-purpose Llama 2 fine-tune with guided reasoning and long conversations

4K contextMac

[View details →](/models/synthia-13b-v1.2)

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

### Wizard LM 13B

13B

General purpose instruction finetune of Llama 2 13B with coding strength

4K contextMac

[View details →](/models/wizardlm-13b-v1.2)

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

### XWin LM 13B

13B

General instruction model fine-tuned with RLHF from Llama 2 13B

4K contextMac

[View details →](/models/xwin-lm-13b-v0.1)

[Browse all models→](/models)

## Frequently asked questions

-   What are the best Llama 2 13B models to run locally on Mac?
    
    Private LLM runs Llama 2 13B models on Mac, fully on-device. Larger variants like Mythomax L2 13B, Spicyboros 13B, Synthia 13B 1.2 need more memory, so the right pick depends on your device's RAM.
    
-   Are Llama 2 13B models private in Private LLM?
    
    Yes. Every Llama 2 13B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
    
-   Do Llama 2 13B models work offline?
    
    Only the one-time download needs a connection. After that, every Llama 2 13B model runs 100% offline in Private LLM.