---
license: apache-2.0
language:
- en
- ro
base_model: nicoboss/Medra27B
datasets:
- nicoboss/medra-medical
tags:
- text-generation
- medical-ai
- summarization
- diagnostic-reasoning
- gemma-3
- fine-tuned
- mlx
- mlx-my-repo
model_size: 27B
version: Medra v1 – Gemma 27B Edition
library_name: peft
author: Dr. Alexandru Lupoi & Nico Bosshard
pipeline_tag: text-generation
---

# Wwayu/Medra27B-mlx-6Bit

The Model [Wwayu/Medra27B-mlx-6Bit](https://huggingface.co/Wwayu/Medra27B-mlx-6Bit) was converted to MLX format from [nicoboss/Medra27B](https://huggingface.co/nicoboss/Medra27B) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Wwayu/Medra27B-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)
```