README.md

---
license: apache-2.0
pipeline_tag: text-generation
arxiv: 2512.24873
tags:
- agent
- moe
- mlx
library_name: mlx
base_model: FutureLivingLab/iFlow-ROME
---

# dokterbob/iFlow-ROME-mlx-mxfp4

This model [dokterbob/iFlow-ROME-mlx-mxfp4](https://huggingface.co/dokterbob/iFlow-ROME-mlx-mxfp4) was
converted to MLX format from [FutureLivingLab/iFlow-ROME](https://huggingface.co/FutureLivingLab/iFlow-ROME)
using mlx-lm version **0.31.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("dokterbob/iFlow-ROME-mlx-mxfp4")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```