---
license: mit
pipeline_tag: image-text-to-text
library_name: transformers
base_model: ServiceNow-AI/Apriel-1.6-15b-Thinker
tags:
- mlx
---

# cnfusion/Apriel-1.6-15b-Thinker-mlx-8Bit

The Model [cnfusion/Apriel-1.6-15b-Thinker-mlx-8Bit](https://huggingface.co/cnfusion/Apriel-1.6-15b-Thinker-mlx-8Bit) was converted to MLX format from [ServiceNow-AI/Apriel-1.6-15b-Thinker](https://huggingface.co/ServiceNow-AI/Apriel-1.6-15b-Thinker) 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("cnfusion/Apriel-1.6-15b-Thinker-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)
```