---
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
- fiction writing
- 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

Experimental brain graft with Mark Twain works, distilled by DavidAU.

This model is a merge of the following models:
- armand0e/Qwen3.5-9B-Fable-5-v1
- DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic

Brainwaves
```brainwaves
          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.622,0.804,0.896
qx86-hi   0.613,0.797,0.892

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     4.375 ± 0.029   16.02 GB      554
qx86-hi   4.247 ± 0.027   15.72 GB      693
```

## Model components

armand0e/Qwen3.5-9B-Fable-5-v1
```brainwaves
          arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.624,0.806,0.891
```

DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic
```brainwaves
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.583,0.761,0.886,0.701,0.424,0.777,0.669
```

## Baseline model

Qwen3.5-9B
```brainwaves
          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.571,0.719,0.895,0.683,0.426,0.770,0.671
```

## Similar model

I created a similar merge with a Nightmedia model as a base:

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Writer-MarkTwain
```brainwaves
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.630,0.814,0.892
qx86-hi  0.639,0.820,0.892

nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder
qx86-hi  0.642,0.819,0.895,0.716,0.454,0.785,0.699
```

The models are being currently evaluated, and will be available soon.


-G

---

# Model recipe

```recipe
models:
  - model: armand0e/Qwen3.5-9B-Fable-5-v1
    parameters:
      weight: 1.6
  - model: DavidAU/Qwen3.5-9B-Mark-Twain-Pro-Writer-Uncensored-Heretic
    parameters:
      weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Fable-MarkTwain
```

---

## 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)
```