---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- vista
- qwen3.5
- vision-language
- gui-grounding
- reinforcement-learning
- mlx
- mlx-my-repo
base_model: inclusionAI/VISTA-4B
metrics:
- accuracy
---

# usermma/VISTA-4B-mlx-5Bit

The Model [usermma/VISTA-4B-mlx-5Bit](https://huggingface.co/usermma/VISTA-4B-mlx-5Bit) was converted to MLX format from [inclusionAI/VISTA-4B](https://huggingface.co/inclusionAI/VISTA-4B) 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("usermma/VISTA-4B-mlx-5Bit")

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)
```