---
language:
- en
- zh
license: mit
base_model: mindlab-research/Macaron-V1-Tall
library_name: transformers
pipeline_tag: text-generation
tags:
- macaron
- macaron-v1
- qwen3.6
- qwen3.6-35b-a3b
- mixture-of-lora
- personal-agent
- tool-use
- generative-ui
- ui4a
- a2ui
- coding-agent
- mlx
- mlx-my-repo
---

# SakaiSec/Macaron-V1-Tall-mlx-2Bit

The Model [SakaiSec/Macaron-V1-Tall-mlx-2Bit](https://huggingface.co/SakaiSec/Macaron-V1-Tall-mlx-2Bit) was converted to MLX format from [mindlab-research/Macaron-V1-Tall](https://huggingface.co/mindlab-research/Macaron-V1-Tall) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("SakaiSec/Macaron-V1-Tall-mlx-2Bit")

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)
```