---
license: apache-2.0
base_model:
- ibm-granite/granite-4.1-8b
- treadon/granite-4.1-8b-Abliterated-AND-Disinhibited
- nightmedia/granite-4.1-8B-TNG-Coder-V11-2800-Heretic
pipeline_tag: text-generation
library_name: transformers
tags:
- finetune
- granite-4.1
- reasoning
- thinking
- emergent
- mlx
---

# granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16

This model was trained on a base of treadon/granite-4.1-8b-Abliterated-AND-Disinhibited.

The training was exclusively in backend development, and took place on DS9, with Spock and Data for Haskell, Worf for Golang, Odo for Python, assisted by Garak, Quark, and Q.

The teacher was a Qwen3.6-35B-A3B with special tuning, profiled to respond in character, think, and serve humour as needed. A second round of training added a rich set of Claude traces, mixed in with lessons already learned.

It has thinking mode by default, unlike the parent model.

```brainwaves
         arc   arc/e boolq hswag obkqa piqa  wino
bf16     0.558,0.760,0.864,0.747,0.440,0.803,0.713
mxfp8    0.559,0.758,0.860,0.744,0.456,0.803,0.727
q8-hi    0.560,0.758,0.863,0.747,0.432,0.803,0.709
q8       0.558,0.759,0.865,0.747,0.440,0.802,0.708
q6-hi    0.561,0.761,0.862,0.747,0.438,0.806,0.708
```

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16")

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)
```