[Models](/models) / [Families](/models/family) / Mixtral 8x7B

# Local Mixtral 8x7B Models for Mac

Run Mixtral 8x7B models fully offline on Mac inside Private LLM — private, with nothing sent to a server.

3 models

![Mistral logo](/model-logos/mistral.svg)

### Dolphin 2.6 Mixtral 8x7B

56B

Uncensored Mixtral 8x7B finetune excelling at coding tasks

33K contextMac

[View details →](/models/dolphin-2.6-mixtral-8x7b)

![Mistral logo](/model-logos/mistral.svg)

### Nous Hermes 2 Mixtral 8x7B DPO

46.7B

General instruction-tuned Mixtral 8x7B model with creative text generation

33K contextMac

[View details →](/models/nous-hermes-2-mixtral-8x7b-dpo)

![Mistral logo](/model-logos/mistral.svg)

### Mixtral 8x7B Instruct v0.1

46.7B

General-purpose assistant outperforming Llama 2 70B

33K contextMac

[View details →](/models/mixtral-8x7b-instruct-v0.1)

[Browse all models→](/models)

## Frequently asked questions

-   What are the best Mixtral 8x7B models to run locally on Mac?
    
    Private LLM runs Mixtral 8x7B models on Mac, fully on-device. Larger variants like Dolphin 2.6 Mixtral 8x7B, Nous Hermes 2 Mixtral 8x7B DPO, Mixtral 8x7B Instruct v0.1 need more memory, so the right pick depends on your device's RAM.
    
-   Are Mixtral 8x7B models private in Private LLM?
    
    Yes. Every Mixtral 8x7B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
    
-   Do Mixtral 8x7B models work offline?
    
    Only the one-time download needs a connection. After that, every Mixtral 8x7B model runs 100% offline in Private LLM.