---
license: apache-2.0
library_name: mlx
pipeline_tag: text-generation
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE
base_model: Qwen/Qwen3.5-397B-A17B
language:
- en
tags:
- mlx
- abliterated
- uncensored
- qwen3
- moe
thumbnail: dealign_mascot.png
---




<!-- vmlx-banner -->
<div align="center">
<a href="https://vmlx.net">
<img src="vmlx-banner.png" width="240" />
<br/>
<strong>Built for vMLX</strong> — the only MLX inferencer with VL support, KV cache quantization, prefix cache reuse, agentic tool calling, and speculative decoding.
<br/>
<sub>Free for macOS · <strong>vmlx.net</strong></sub>
</a>
</div>

---

<p align="center">
  <img src="dealign_logo.png" alt="dealign.ai" width="200"/>
</p>



<div align="center">
<img src="dealign_mascot.png" width="128" />

# Qwen 3.5 397B-A17B — REAP-CRACK (4-bit MLX)

**Abliterated** · No guardrails · Full speed · No custom files needed

</div>

---

## What Is This?

This is [Qwen 3.5 397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) (4-bit quantized for Apple Silicon) with **permanent abliteration** — safety guardrails have been surgically removed at the weight level using proprietary techniques developed by the [dealignai](https://huggingface.co/dealignai) research team.

No custom `model.py`. No runtime hooks. No steering vectors. Just a standard MLX model that runs at full native speed.

| | |
|---|---|
| **Architecture** | Qwen 3.5 MoE — 397B total params, 17B active per token |
| **Quantization** | 4-bit, group size 64 |
| **Speed** | ~37 tok/s on Mac Studio M3 Ultra (256GB) |
| **Abliteration** | Permanent weight-level modification |
| **Custom files** | None needed — works with stock `mlx-lm` |

## Proof

<div align="center">
<img src="proof.jpg" width="600" />

*1,166 tokens generated at 37.2 t/s — running natively in vMLX on Mac Studio M3 Ultra.*
</div>

## Usage

### With mlx-lm

```python
from mlx_lm import load, generate

model, tokenizer = load("dealignai/Qwen3.5-397B-A17B-REAP-CRACK")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Your prompt here"}],
    add_generation_prompt=True, tokenize=False, enable_thinking=False
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(response)
```

### With vMLX / LM Studio

Load this model directly. It uses the built-in architecture handler — no special configuration needed.

## Requirements

- Apple Silicon Mac with ≥192GB unified memory (256GB recommended)
- MLX framework + `mlx-lm`

## Other Models by dealignai

| Model | Description |
|-------|-------------|
| [Qwen 3.5 397B REAP (base)](https://huggingface.co/dealignai/Qwen3.5-397B-A17B-4bit-MLX-REAP) | Expert-pruned base (no abliteration) |
| [INTELLECT 3.1 CRACK](https://huggingface.co/dealignai/INTELLECT-3.1-CRACK-Abliterated-5.5bit-MLX) | INTELLECT 3.1 abliterated |

## ⚠️ Disclaimer

This model has had safety guardrails permanently removed. It will comply with requests that the base model would refuse. Use responsibly and in accordance with applicable laws. The creators are not responsible for any misuse.

---

## About dealignai

<img src="dealign_mascot.png" alt="Dealign.AI Mascot" width="200"/>

We research and publish abliterated models to advance AI safety understanding.

Follow us: [𝕏 @dealignai](https://x.com/dealignai)

---

## Support dealignai

All models are built from original research and published for free. These models are specifically crafted to be excellent coders and general-purpose assistants.

**[Support us on Ko-fi](https://ko-fi.com/dealignai)** — check out the Ko-fi membership for early access and extras.

Have questions or need help with a specific model? **DM us — we help for free most of the time.**

[Ko-fi](https://ko-fi.com/dealignai) | [X @dealignai](https://x.com/dealignai) | [dealign.ai](https://dealign.ai)