--- title: MAI-UI-2B-bf16-v2 canonical_url: "https://www.modelscope.cn/models/mlx-community/MAI-UI-2B-bf16-v2" md_url: "https://www.modelscope.cn/models/mlx-community/MAI-UI-2B-bf16-v2.md" repository: mlx-community/MAI-UI-2B-bf16-v2 last_updated: 2026-03-21 license: apache-2.0 pipeline_tag: image-text-to-text tasks: - image-text-to-text model_type: - qwen3_vl architectures: - Qwen3VLForConditionalGeneration base_model: - Tongyi-MAI/MAI-UI-2B base_model_relation: finetune parameters: 2.1B tensor_type: - BF16 library_name: - mlx - safetensors - pytorch frameworks: - pytorch language: - en downloads: 38 stars: 0 tags: - mlx - mlx-vlm - safetensors - apple-silicon - conversational - gui - vision-language-model - qwen3_vl - mai-ui - grounding - mobile-navigation - computer-use - agent - 2b - bf16 --- # MAI-UI-2B-bf16-v2 > MAI-UI-2B-bf16-v2 - mlx-community 在 ModelScope 开源的模型。This is an MLX conversion of Tongyi-MAI/MAI-UI-2B, optimized for Apple Silicon. mlx-community/MAI-UI-2B-bf16-v2 是 ModelScope 魔搭社区上的 2.1B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 Tongyi-MAI/MAI-UI-2B 构建。 - **Repository**: mlx-community/MAI-UI-2B-bf16-v2 - **License**: apache-2.0 - **Tasks**: image-text-to-text - **Parameters**: 2.1B - **Base model**: Tongyi-MAI/MAI-UI-2B - **Tags**: mlx, mlx-vlm, safetensors, apple-silicon, conversational, gui, vision-language-model, qwen3_vl, mai-ui, grounding, mobile-navigation, computer-use, agent, 2b, bf16 - **Downloads**: 38 - **Stars**: 0 - **Last updated**: 2026-03-21 Source: https://www.modelscope.cn/models/mlx-community/MAI-UI-2B-bf16-v2 --- # MAI-UI-2B bf16 This is an MLX conversion of [Tongyi-MAI/MAI-UI-2B](https://huggingface.co/Tongyi-MAI/MAI-UI-2B), 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-2B` | | 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 @ 48b51ed)` | | Quantization | `bf16` | | Group size | `n/a` | | Quantization mode | `n/a` | | Artifact size | `4.0G` | | 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 refreshed artifact is intended to supersede the older nested `mlx-community/MAI-UI-2B-bf16` line for clean serving-path and benchmark use. ## Validation This artifact passed local validation in this workspace: - `mlx_vlm` prompt-packet validation: `PASS` - `vllm-mlx` OpenAI-compatible serve validation: `PASS` Local validation notes: - the Track A packet remained usable on the `2B` line - grounding and structured-action rows stayed on the correct `API Host` target - the main remaining defect was action wording precision, not target collapse ## Performance - Artifact size on disk: `4.0G` - Local fixed-packet `mlx_vlm` validation used about `5.29 GB` average peak memory - Observed local fixed-packet throughput was about `469-608` prompt tok/s and `2.5-15.2` generation tok/s across the four validation prompts These are local validation measurements, not a full benchmark suite. ## Usage ### Install ```bash pip install -U mlx-vlm ``` ### CLI ```bash python -m mlx_vlm.generate \ --model mlx-community/MAI-UI-2B-bf16-v2 \ --image path/to/image.png \ --prompt "Describe the visible controls on this screen." \ --max-tokens 256 \ --temperature 0.0 ``` ### Python ```python from mlx_vlm import load, generate model, processor = load("mlx-community/MAI-UI-2B-bf16-v2") 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 ```bash python -m vllm_mlx.cli serve mlx-community/MAI-UI-2B-bf16-v2 --mllm --localhost --port 8000 ``` ## Links - Upstream model: [Tongyi-MAI/MAI-UI-2B](https://huggingface.co/Tongyi-MAI/MAI-UI-2B) - Paper: [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://arxiv.org/abs/2512.22047) - Project page: [tongyi-mai.github.io/MAI-UI](https://tongyi-mai.github.io/MAI-UI/) - GitHub: [Tongyi-MAI/MAI-UI](https://github.com/Tongyi-MAI/MAI-UI) - MLX framework: [ml-explore/mlx](https://github.com/ml-explore/mlx) - mlx-vlm: [Blaizzy/mlx-vlm](https://github.com/Blaizzy/mlx-vlm) ## Other Quantizations Planned sibling repos in this Track C refresh: - [`mlx-community/MAI-UI-2B-bf16-v2`](https://huggingface.co/mlx-community/MAI-UI-2B-bf16-v2) - this model - [`mlx-community/MAI-UI-2B-6bit-v2`](https://huggingface.co/mlx-community/MAI-UI-2B-6bit-v2) Not published from this wave: - `4bit` was evaluated locally and rejected after runtime validation ## 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. - This refreshed `bf16` artifact is the local reference artifact for the accepted `6bit` variant in Track C. - Final public Track C comparative benchmarking happens after the refreshed `2B` repos are uploaded. ## Citation If you use this MLX conversion, please also cite the original MAI-UI work: ```bibtex @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-2B](https://huggingface.co/Tongyi-MAI/MAI-UI-2B).