---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
library_name: transformers
base_model: Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
tags:
- mlx
---

# mrtoots/Tongyi-DeepResearch-30B-A3B-mlx-8Bit

The Model [mrtoots/Tongyi-DeepResearch-30B-A3B-mlx-8Bit](https://huggingface.co/mrtoots/Tongyi-DeepResearch-30B-A3B-mlx-8Bit) was converted to MLX format from [Alibaba-NLP/Tongyi-DeepResearch-30B-A3B](https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B) using mlx-lm version **0.26.4**.


## Toots' Note:
This model was converted and quantized utilizing Alibaba-NLP's base version of Tongyi-DeepResearch-30B-A3B.

Please follow and support [Alibaba-NLP's work](https://huggingface.co/Alibaba-NLP) if you like it!

🦛 <span style="color:#800080">If you want a free consulting session, </span>[fill out this form](https://forms.gle/xM9gw1urhypC4bWS6) <span style="color:#800080">to get in touch!</span> 🤗



## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mrtoots/Tongyi-DeepResearch-30B-A3B-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)
```