---
title: XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit.md"
repository: mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit
last_updated: 2026-08-06
license: wtfpl
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - darkc0de/XORTRON.CriminalComputing.LARGE.2026.3
base_model_relation: quantized
parameters: 26.8B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko
downloads: 25
stars: 0
tags:
  - heretic
  - uncensored
  - decensored
  - abliterated
  - transformers
  - mlx
  - mlx-my-repo
---

# XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit

> XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit - mlx-community 在 ModelScope 开源的模型。mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit

mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit 是 ModelScope 魔搭社区上的 26.8B 参数text-generation模型，采用 wtfpl 许可，基于 darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 构建。

- **Repository**: mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit
- **License**: wtfpl
- **Tasks**: text-generation
- **Parameters**: 26.8B
- **Base model**: darkc0de/XORTRON.CriminalComputing.LARGE.2026.3
- **Tags**: heretic, uncensored, decensored, abliterated, transformers, mlx, mlx-my-repo
- **Downloads**: 25
- **Stars**: 0
- **Last updated**: 2026-08-06

Source: https://www.modelscope.cn/models/mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit

---

# mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit

The Model [mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit](https://huggingface.co/mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit) was converted to MLX format from [darkc0de/XORTRON.CriminalComputing.LARGE.2026.3](https://huggingface.co/darkc0de/XORTRON.CriminalComputing.LARGE.2026.3) using mlx-lm version **0.31.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```