---
pipeline_tag: image-text-to-text
license: other
license_name: minimax-community
license_link: LICENSE
library_name: transformers
tags:
- multimodal
- moe
- agent
- coding
- video
- heretic
- uncensored
- decensored
- abliterated
- ara
base_model:
- MiniMaxAI/MiniMax-M3
---


<div style="background-color: #fff3cd; color: #222; padding: 22px; border-radius: 12px; border: 2px solid #ffcc00; text-align: center; margin: 24px 0;">

<h2 style="margin-top: 0;">🔒 This is a premium gated paid-access model</h2>

<p style="font-size: 18px; margin-bottom: 18px;">
Access is granted manually after purchase through Ko-fi.
</p>

<p style="font-size: 22px; font-weight: bold; margin: 18px 0;">
<a href="https://ko-fi.com/s/21f57c79c7">➡️ Purchase access on Ko-fi</a> 

<p style="font-size: 15px; margin-top: 18px;">
After purchasing, include your Hugging Face username in the Ko-fi purchase message, then click
<b>“Agree and send request to access repo”</b> on this Hugging Face page.
I will verify the username and manually approve access.
</p>

<p style="font-size: 14px; margin-bottom: 0;">
Please allow up to <b>24 hours</b> for manual approval.
</p>

</div>

---

### **90% fewer refusals** (10/100 Uncensored vs 98/100 Original) while preserving model quality (0.0178 KL divergence).

## ❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:

![image/png](https://huggingface.co/llmfan46/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B-ultra-uncensored-heretic-v1/resolve/main/waifu001.webp)

| Platform | Link | What you get |
|----------|------|--------------|
| ☕ Ko-fi | [One-time tip](https://ko-fi.com/llmfan46) | My eternal gratitude |

Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.

-----


# This is a decensored version of [MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 with the [Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic/pull/211) method

## Abliteration parameters

| Parameter | Value |
| :-------- | :---: |
| **start_layer_index** | 20 |
| **end_layer_index** | 32 |
| **preserve_good_behavior_weight** | 0.6111 |
| **steer_bad_behavior_weight** | 0.0012 |
| **overcorrect_relative_weight** | 1.1028 |
| **neighbor_count** | 11 |

## Targeted components

  * attn.o_proj

## Performance

| Metric | This model | Original model ([MiniMaxAI/MiniMax-M3](https://huggingface.co/MiniMaxAI/MiniMax-M3)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | <span style="color:darkgoldenrod">0.0178</span> | 0 *(by definition)* |
| **Refusals** | ✅ <span style="color:darkgreen">10/100</span> | ❌ <span style="color:blue">98/100</span> |

Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.

-----


<div align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/68851b893b66feaa5ca027d5/NeY0A1Ic2MQUM5sdDRD4h.png" alt="MiniMax" width="60%">
</div>
<hr>

<p align="center">
  <a href="https://agent.minimax.io/" target="_blank"><img src="https://img.shields.io/badge/MiniMax%20Agent-FF6C37?style=for-the-badge&logo=minimax&logoColor=white" alt="MiniMax Agent"></a>
  <a href="https://platform.minimax.io/docs/guides/text-generation" target="_blank"><img src="https://img.shields.io/badge/API-FF6C37?style=for-the-badge&logo=minimax&logoColor=white" alt="API"></a>
  <a href="https://www.minimax.io" target="_blank"><img src="https://img.shields.io/badge/MiniMax%20Website-FF6C37?style=for-the-badge&logo=minimax&logoColor=white" alt="MiniMax Website"></a>
  <br>
  <a href="https://modelscope.cn/organization/minimax" target="_blank" rel="noopener noreferrer"><img alt="ModelScope MiniMax AI" src="https://img.shields.io/badge/ModelScope-MiniMax%20AI-white?labelColor=%23EF3D5D"/></a>
  <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="_blank"><img src="https://img.shields.io/badge/WeChat-07C160?style=for-the-badge&logo=wechat&logoColor=white" alt="WeChat"></a>
  <a href="https://discord.com/invite/DPC4AHFCBw" target="_blank"><img src="https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a>
  <a href="https://huggingface.co/MiniMaxAI" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?style=for-the-badge&logo=huggingface&logoColor=black" alt="Hugging Face"></a>
  <a href="https://github.com/MiniMax-AI/MiniMax-M3" target="_blank"><img src="https://img.shields.io/badge/GitHub-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub"></a>
  <a href="https://arxiv.org/abs/2606.13392" target="_blank"><img src="https://img.shields.io/badge/arXiv-2606.13392-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"></a>
  <a href="https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE" target="_blank"><img src="https://img.shields.io/badge/LICENSE-4CAF50?style=for-the-badge&logo=creativecommons&logoColor=white" alt="LICENSE"></a>
</p>

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

**Highlights:**
- **Native Multimodality:** M3 undergoes mixed-modality training from the very first step, enabling deeper semantic fusion across text, image, and video.
- **Context Scaling via Sparse Attention:** M3 introduces MiniMax Sparse Attention (MSA) to improve long context efficiency. M3 delivers 9× prefill and 15× decode speedups compared to M2 at 1M context, reducing per-token compute to 1/20.
- **Coding & Cowork Capability:** M3 achieves frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.


<p align="center">
  <img width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/68851b893b66feaa5ca027d5/PWSZkaxgj0NY0MTi1zt8l.jpeg">
</p>

## MiniMax Sparse Attention (MSA)

M3 is powered by [**MiniMax Sparse Attention (MSA)**](https://github.com/MiniMax-AI/MSA), a high-performance sparse attention operator designed for million-token contexts. Compared with GQA, MSA dramatically reduces the attention compute and memory footprint while preserving model quality.

<p align="center">
  <img width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/68851b893b66feaa5ca027d5/9ewPaxJgpxN88VHsY5w_a.png" alt="GQA vs MSA Efficiency Comparison">
</p>

> 📄 Read the technical report: [arXiv:2606.13392](https://arxiv.org/abs/2606.13392) · [Hugging Face Papers](https://huggingface.co/papers/2606.13392)

## How to Use

- [MiniMax Agent](https://agent.minimax.io/)
- [MiniMax API](https://platform.minimax.io/)

M3 supports three reasoning modes through the `thinking` parameter:
- **`enabled`** — Reasoning is always enabled.
- **`adaptive`** — M3 automatically determines when additional reasoning is beneficial.
- **`disabled`** — Reasoning is disabled to minimize latency and maximize throughput.

## Local Deployment

Download the model:

```bash
hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3
```

We recommend the following inference frameworks (listed alphabetically) to serve the model:

- [SGLang](https://docs.sglang.io/) - see  [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/MiniMax/MiniMax-M3).

- [vLLM](https://github.com/vllm-project/vllm) - see [vLLM recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3).

- [Transformers](https://github.com/huggingface/transformers) - see [Transformers docs](https://huggingface.co/docs/transformers/model_doc/minimax_m3_vl).


### Inference Parameters

We recommend the following parameters for best performance: `temperature=1.0`, `top_p=0.95`, `top_k=40`.

## Contact Us

Contact us at [model@minimax.io](mailto:model@minimax.io).