---
language:
- en
- zh
license: apache-2.0
tags:
- unsloth
- nightmedia
- fine tune
- heretic
- abliterated
- uncensored
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prosing
- vivid writing
- fiction
- roleplaying
- bfloat16
- all use cases
- Deckard(qx)
- merge
- mergekit
- mlx
library_name: transformers
pipeline_tag: image-text-to-text
base_model:
- armand0e/Qwen3.5-9B-Fable-5-v1
- DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic
- nightmedia/Qwen3.5-9B-Fable-MarkTwain
---

# Qwen3.5-9B-Fable-MarkTwain-qx86-hi-mlx

This model [Qwen3.5-9B-Fable-MarkTwain-qx86-hi-mlx](https://huggingface.co/Qwen3.5-9B-Fable-MarkTwain-qx86-hi-mlx) was
converted to MLX format from [['armand0e/Qwen3.5-9B-Fable-5-v1', 'DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic', 'nightmedia/Qwen3.5-9B-Fable-MarkTwain']](https://huggingface.co/['armand0e/Qwen3.5-9B-Fable-5-v1', 'DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic', 'nightmedia/Qwen3.5-9B-Fable-MarkTwain'])
using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3.5-9B-Fable-MarkTwain-qx86-hi-mlx")

prompt = "hello"

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

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