mlx-community/MAI-UI-8B-bf16

MAI-UI-8B bf16

This is an MLX conversion of Tongyi-MAI/MAI-UI-8B, optimized for Apple Silicon.

MAI-UI is a family of real-world centric foundation GUI agents built for grounding, GUI navigation, user interaction, and broader device-cloud agent workflows. The family spans multiple scales and is framed upstream around realistic deployment, including user interaction, MCP-style tool use, online RL, and device-cloud collaboration.

This MLX artifact was converted with mlx-vlm and validated locally with both mlx_vlm prompt-packet checks and vllm-mlx OpenAI-compatible serve checks.

Conversion Details

Field	Value
Upstream model	Tongyi-MAI/MAI-UI-8B
Artifact type	bf16 MLX conversion
Conversion tool	mlx_vlm.convert via mlx-vlm 0.3.12
Python	3.11.14
MLX	0.31.0
Transformers	5.2.0
Validation backend	vllm-mlx (phase/p1 @ 8a5d41b)
Quantization	bf16
Group size	n/a
Quantization mode	n/a
Artifact size	16.34G
Template repair	tokenizer_config.json["chat_template"] was re-injected from chat_template.jinja after conversion

Additional notes:

• Root-level packaging is intentional for vllm-mlx multimodal detection compatibility.
• processor_config.json and video_preprocessor_config.json are present at repo root.
• This artifact intentionally augments tokenizer-visible template metadata for downstream compatibility checks.

Validation

This artifact passed local validation in this workspace:

• mlx_vlm prompt-packet validation: PASS
• vllm-mlx OpenAI-compatible serve validation: PASS

Local validation note:

• the structured-action prompt omitted the requested reason field even in bf16; this was treated as a model-output characteristic, not a conversion defect

Performance

• Artifact size on disk: 16.34G
• Local fixed-packet mlx_vlm validation used about 30.55 GB peak memory
• Observed local fixed-packet throughput was about 225-249 prompt tok/s and 20.9-21.9 generation tok/s across the four validation prompts

These are local validation measurements, not a full benchmark suite.

Usage

Install

pip install -U mlx-vlm

CLI

python -m mlx_vlm.generate \
  --model mlx-community/MAI-UI-8B-bf16 \
  --image path/to/image.png \
  --prompt "Describe the visible controls on this screen." \
  --max-tokens 256 \
  --temperature 0.0

Python

from mlx_vlm import load, generate

model, processor = load("mlx-community/MAI-UI-8B-bf16")
result = generate(
    model,
    processor,
    prompt="Describe the visible controls on this screen.",
    image="path/to/image.png",
    max_tokens=256,
    temp=0.0,
)
print(result.text)

vllm-mlx Serve

python -m vllm_mlx.cli serve mlx-community/MAI-UI-8B-bf16 --mllm --localhost --port 8000

Links

• Upstream model: Tongyi-MAI/MAI-UI-8B
• Paper: MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
• Project page: tongyi-mai.github.io/MAI-UI
• GitHub: Tongyi-MAI/MAI-UI
• MLX framework: ml-explore/mlx
• mlx-vlm: Blaizzy/mlx-vlm

Other Quantizations

Planned sibling repos in this wave:

• mlx-community/MAI-UI-8B-bf16 - this model
• mlx-community/MAI-UI-8B-6bit
• mlx-community/MAI-UI-8B-4bit

Notes and Limitations

• This card reports local MLX conversion and validation results only.
• Upstream benchmark claims belong to the original MAI-UI model family and were not re-run here unless explicitly stated.
• Throughput and memory vary with prompt length, image resolution, and runtime settings.
• This bf16 artifact is the local reference artifact for the 6bit and 4bit variants in this wave.

Citation

If you use this MLX conversion, please also cite the original MAI-UI work:

@misc{zhou2025maiuitechnicalreportrealworld,
  title={MAI-UI Technical Report: Real-World Centric Foundation GUI Agents},
  author={Hanzhang Zhou and Xu Zhang and Panrong Tong and Jianan Zhang and Liangyu Chen and Quyu Kong and Chenglin Cai and Chen Liu and Yue Wang and Jingren Zhou and Steven Hoi},
  year={2025},
  eprint={2512.22047},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2512.22047},
}

License

This repo follows the upstream model license: Apache 2.0. See the upstream model card for the authoritative license details: Tongyi-MAI/MAI-UI-8B.