[Models](/models) / [Llama 3.2 3B](/models?family=Llama%203.2%203B#models-gallery) / Llama 3.2 3B Instruct Abliterated

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

# Run Llama 3.2 3B Instruct Abliterated on iPhone, iPad & Mac

Llama 3.2 3B Instruct Abliterated runs 100% private on iPhone, iPad & Mac inside Private LLM — no internet connection required, no data sent to any server.

3.6BiPhoneiPadMac

## Download the quantized weights

These are the exact OmniQuant weights Private LLM runs for Llama 3.2 3B Instruct Abliterated, published on our Hugging Face org. They're standard weights you can load in any app that supports the format, not just Private LLM.

-   [iPhone & iPad — 4-bit OmniQuant →](https://huggingface.co/numen-tech/Llama-3.2-3B-Instruct-abliterated-w4a16g128asym)
-   [Mac — 4-bit OmniQuant →](https://huggingface.co/numen-tech/Llama-3.2-3B-Instruct-abliterated-w4a16g128asym)

## Specifications

Parameters

3.6B

Context window

131K tokens

License

Llama 3.2

Quantization

OmniQuant 4-bit

Family

Llama 3.2 3B

## What Llama 3.2 3B Instruct Abliterated is good at

[uncensored](/models/uncensored)

This is an uncensored version of the Llama 3.2 3B Instruct model, modified using a technique called abliteration to remove refusals. It performs similarly to the original model on standard benchmarks like IF Eval and MMLU Pro. The model is good for tasks where you want fewer content restrictions while maintaining general language understanding.

## 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 12 Pro / 12 Pro 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 mini (A17 Pro)iPad (A16)

### Mac

Mac (Apple Silicon, 192GB)MacBook Pro (M4 Max, 128GB)Mac Studio / Pro (Apple Silicon, 96GB)MacBook Pro (M4 Max, 64GB)MacBook Pro (M4 Max, 48GB)MacBook Pro (M4 Max, 36GB)Mac (Apple Silicon, 32GB)MacBook Air (M4, 24GB)MacBook Air (M-series, 16GB)Mac (Apple Silicon, 8GB)

Browse every model that fits [iPhone](/models/best-for-iphone) or [Mac](/models/best-for-mac).

## How to run Llama 3.2 3B Instruct Abliterated in Private LLM

1.  Download Private LLM from the App Store.
2.  Open the in-app model library and choose Llama 3.2 3B Instruct Abliterated.
3.  Download the model once, then chat fully offline.

[![Download Private LLM on the App Store](/app-store/download-badge/en/download.svg)![Download Private LLM on the App Store](/app-store/download-badge/en/download-dark.svg)](/download)[Join our Discord](/discord)

## Variants & related models

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

### Dolphin 3.0 Llama 3.2 3B

3B

uncensored

131K contextiPhone & iPad · Mac

[View details →](/models/dolphin3.0-llama3.2-3b)

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

### FuseChat Llama 3.2 3B Instruct

3.2B

general

131K contextiPhone & iPad · Mac

[View details →](/models/fusechat-llama-3.2-3b-instruct)

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

### Hermes 3 Llama 3.2 3B

3.2B

general

131K contextiPhone & iPad · Mac

[View details →](/models/hermes-3-llama-3.2-3b)

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

### Meta Llama 3.2 3B Instruct

3.2B

general

iPhone & iPad · Mac

[View details →](/models/llama-3.2-3b-instruct)

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

### Llama 3.2 3B Instruct Uncensored

3B

uncensored

131K contextiPhone & iPad · Mac

[View details →](/models/llama-3.2-3b-instruct-uncensored)

![Google Gemma logo](/model-logos/gemma.svg)

### Amoral Gemma 3 1B v2

1B

uncensored

33K contextiPhone & iPad · Mac

[View details →](/models/amoral-gemma3-1b-v2)

## Frequently asked questions

-   Can I run Llama 3.2 3B Instruct Abliterated on iPhone?
    
    Yes. Llama 3.2 3B Instruct Abliterated 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 12 Pro / 12 Pro Max, fully on-device in Private LLM — no internet connection required.
    
-   Can I run Llama 3.2 3B Instruct Abliterated on Mac?
    
    Yes. Llama 3.2 3B Instruct Abliterated runs on Macs with enough unified memory, such as Mac (Apple Silicon, 192GB), MacBook Pro (M4 Max, 128GB), Mac Studio / Pro (Apple Silicon, 96GB), MacBook Pro (M4 Max, 64GB), MacBook Pro (M4 Max, 48GB), MacBook Pro (M4 Max, 36GB), Mac (Apple Silicon, 32GB), MacBook Air (M4, 24GB), MacBook Air (M-series, 16GB), Mac (Apple Silicon, 8GB), fully on-device in Private LLM.
    
-   Does Llama 3.2 3B Instruct Abliterated work offline?
    
    Yes. Once downloaded in Private LLM, Llama 3.2 3B Instruct Abliterated runs 100% on-device — no internet connection, and nothing is sent to any server.
    
-   Is Llama 3.2 3B Instruct Abliterated free to use?
    
    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 Llama 3.2 3B Instruct Abliterated in Private LLM

Private LLM has run local AI on iPhone, iPad, and Mac since 2023, before Apple Intelligence existed. Inference happens on your device, so your Llama 3.2 3B Instruct Abliterated conversations never reach a server. The part most apps gloss over is quantization, and that is exactly where on-device quality is won or lost. Most llama.cpp and MLX wrappers ship the same off-the-shelf 4-bit RTN weights. Private LLM ships GPTQ and OmniQuant quantization, tuned per model, and our 3-bit OmniQuant models match or beat those 4-bit RTN builds on the same Apple Silicon. Run the same model both ways and you feel it in the first reply. [See how our quantization works](/en/faq#Why-can-t-Private-LLM-load-models-directly-from-Hugging-Face).

### More from Numen

[![Slop or Not app icon](/app-icons/slop-or-not.png)

#### Slop or Not

Catch AI-written text on iPhone and Mac. The check runs on-device, so nothing you paste gets uploaded.

](https://slopornot.ai)[![Clean Links app icon](/app-icons/clean-links.png)

#### Clean Links

Strip trackers and clutter from any link before you share it. The cleanup happens on your device.

](https://cleanlinks.app)

Specifications and summary come from Llama 3.2 3B Instruct Abliterated's [Hugging Face model card](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated), released under the Llama 3.2 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.