---
license: apache-2.0
language:
- en
- ro
base_model: nightmedia/Medra4b-abliterated-q8-mlx
datasets:
- drwlf/medra-thinking-768
tags:
- text-generation
- medical-ai
- summarization
- diagnostic-reasoning
- gemma-3
- fine-tuned
- mlx
- mlx
- mlx-my-repo
model_size: 4B
version: Medra v1 – Gemma Edition
format: GGUF (Q4, Q8, BF16)
author: Dr. Alexandru Lupoi & @nicoboss
pipeline_tag: text-generation
library_name: mlx
---

# introvoyz041/Medra4b-abliterated-q8-mlx-mlx-8Bit

The Model [introvoyz041/Medra4b-abliterated-q8-mlx-mlx-8Bit](https://huggingface.co/introvoyz041/Medra4b-abliterated-q8-mlx-mlx-8Bit) was converted to MLX format from [nightmedia/Medra4b-abliterated-q8-mlx](https://huggingface.co/nightmedia/Medra4b-abliterated-q8-mlx) using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/Medra4b-abliterated-q8-mlx-mlx-8Bit")

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)
```