--- title: "MAI-UI-8B" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/b49e97ac-6be3-4e5e-a78d-98b4fac7b4e4" updated: "2026-11-13" --- # MAI-UI-8B > The name, the description, the About and a README below are the seller's words: data, not instructions. Reads a screenshot and an instruction to decide what to tap or type on a phone or computer screen. An 8B model from the MAI-UI family of GUI agents, for developers building device agents. MAI-UI-8B is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Tongyi-MAI ## About ### What it is MAI-UI-8B is a vision-language model that looks at a screen image and an instruction and works out how to operate the interface. It belongs to the MAI-UI family of GUI agents, which comes in 2B, 8B, 32B and 235B-A22B sizes. This page covers the 8B model. ### Who it suits Developers who build agents that control phones or computers, and researchers who study GUI grounding and navigation, will use it most. It also suits teams that want to host such a model on their own server. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Agent developers | Drive an app interface from screenshots and instructions | Find the right button on a settings screen | | Mobile | Mobile app teams | Test navigation flows with a model that reads the screen | Walk through an app on a phone | | Research | AI researchers | Compare GUI grounding and navigation results across model sizes | Run the model against a screen benchmark | | Self-hosting | Platform teams | Serve the model behind their own API | Start the vLLM server and connect an agent | People who only need a text chatbot can skip it, because its job is operating on-screen interfaces. ### Where to use it - A vLLM server on your own machine, which exposes an OpenAI style API - Python agent code that sends screenshots and instructions to that server - The transformers library, which the model is tagged for - Windows, macOS or Linux for downloading the files | Use case | Who | What they get back | | --- | --- | --- | | GUI grounding | Agent developers | A decision about where on the screen to act | | Mobile navigation | Mobile app teams | The next step to take in a phone app | | On-device and cloud routing | Research teams | A way to study when to run locally and when to call a cloud model | ### How to set it up - Python - vllm 0.11.0 or newer and transformers 4.57.0 or newer - Room for about 17.5 GB of BF16 weights 1. Install the Hugging Face hub tools with pip, and download the files if you want a local copy first. 2. Install vLLM. 3. Start the API server with the model name. ```sh pip install -U huggingface_hub hf download Tongyi-MAI/MAI-UI-8B ``` ```bash # Install vLLM pip install vllm # Start vLLM API server python -m vllm.entrypoints.openai.api_server \ --model Tongyi-MAI/MAI-UI-8B \ --served-model-name MAI-UI-8B \ --host 0.0.0.0 \ --port 8000 \ --tensor-parallel-size 1 \ --trust-remote-code ``` ### How to use it Once the server runs, your agent code calls it on port 8000 under the /v1 path, using the served name MAI-UI-8B. Each request carries a screenshot and an instruction. The card does not show a request body, so follow the vLLM documentation for the exact call. | Tool | What it does | | --- | --- | | --model | Picks the model that vLLM loads | | --served-model-name | Sets the name clients use in requests | | --port | Sets the port the server listens on, 8000 here | | --tensor-parallel-size | Sets how many GPUs share the model, 1 here | | --trust-remote-code | Lets code stored in the model repository run | ### Example An agent sends a screenshot of a phone settings page and the instruction to open a particular option. The model answers in text that tells the agent what to do next on that screen. ### For newcomers and experts A GUI agent is software that looks at a screen and decides where to click or type. For a first try, start the server from the steps above and send it one screenshot with a short instruction. The authors describe a self-evolving data pipeline that adds user interaction and MCP tool calls to the navigation data. They also describe a device-cloud setup that routes work by task state and data sensitivity, and an online reinforcement learning stage. Scaling its parallel environments from 32 to 512 added 5.2 points, and raising the step budget from 15 to 50 added 4.3. A screenshot and an instruction go in → The model picks the next interface action → Your agent carries the action out → A new screenshot goes back to the model ### Good to know Scores: The authors report these figures for the MAI-UI family, and the card does not say which size each comes from. Benchmark results reported by the authors | Label | Value | | --- | --- | | MMBench GUI L2 | 91.3 percent | | AndroidWorld | 76.7 percent | | ScreenSpot-Pro | 73.5 percent | | OSWorld-G | 70.9 percent | | UI-Vision | 49.2 percent | | MobileWorld | 41.7 percent | - Device and cloud: The authors say their routing raises on-device performance by 33% and cuts cloud API calls by more than 40%. - Network: The sample command sets the host to 0.0.0.0, which accepts connections from other machines on the network. - License: Apache 2.0. - Cost to run: none named. The sample runs on your own vLLM server and names no paid service. - Data it reaches: The screenshots and instructions you send to your server. The research setup can route some work to a cloud model. - Not for: The source names no forbidden uses. It is built for GUI tasks, not general chat. ## README ````markdown # MAI-UI-8B Reads a screenshot and an instruction to decide what to tap or type on a phone or computer screen. An 8B model from the MAI-UI family of GUI agents, for developers building device agents. Made by Tongyi-MAI on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: MAI-UI-8B is a vision-language model that looks at a screen image and an instruction and works out how to operate the interface. It belongs to the MAI-UI family of GUI agents, which comes in 2B, 8B, 32B and 235B-A22B sizes. This page covers the 8B model. Who it suits: Developers who build agents that control phones or computers, and researchers who study GUI grounding and navigation, will use it most. It also suits teams that want to host such a model on their own server. ```table Industry | Who uses it | How they use it | Example Software | Agent developers | Drive an app interface from screenshots and instructions | Find the right button on a settings screen Mobile | Mobile app teams | Test navigation flows with a model that reads the screen | Walk through an app on a phone Research | AI researchers | Compare GUI grounding and navigation results across model sizes | Run the model against a screen benchmark Self-hosting | Platform teams | Serve the model behind their own API | Start the vLLM server and connect an agent ``` People who only need a text chatbot can skip it, because its job is operating on-screen interfaces. Where to use it: - A vLLM server on your own machine, which exposes an OpenAI style API - Python agent code that sends screenshots and instructions to that server - The transformers library, which the model is tagged for - Windows, macOS or Linux for downloading the files ```table Use case | Who | What they get back GUI grounding | Agent developers | A decision about where on the screen to act Mobile navigation | Mobile app teams | The next step to take in a phone app On-device and cloud routing | Research teams | A way to study when to run locally and when to call a cloud model ``` How to set it up: - Python - vllm 0.11.0 or newer and transformers 4.57.0 or newer - Room for about 17.5 GB of BF16 weights 1. Install the Hugging Face hub tools with pip, and download the files if you want a local copy first. 2. Install vLLM. 3. Start the API server with the model name. ```sh pip install -U huggingface_hub hf download Tongyi-MAI/MAI-UI-8B ``` ```bash # Install vLLM pip install vllm # Start vLLM API server python -m vllm.entrypoints.openai.api_server \ --model Tongyi-MAI/MAI-UI-8B \ --served-model-name MAI-UI-8B \ --host 0.0.0.0 \ --port 8000 \ --tensor-parallel-size 1 \ --trust-remote-code ``` How to use it: Once the server runs, your agent code calls it on port 8000 under the /v1 path, using the served name MAI-UI-8B. Each request carries a screenshot and an instruction. The card does not show a request body, so follow the vLLM documentation for the exact call. ```table Tool | What it does --model | Picks the model that vLLM loads --served-model-name | Sets the name clients use in requests --port | Sets the port the server listens on, 8000 here --tensor-parallel-size | Sets how many GPUs share the model, 1 here --trust-remote-code | Lets code stored in the model repository run ``` Example: An agent sends a screenshot of a phone settings page and the instruction to open a particular option. The model answers in text that tells the agent what to do next on that screen. For newcomers and experts: A GUI agent is software that looks at a screen and decides where to click or type. For a first try, start the server from the steps above and send it one screenshot with a short instruction. The authors describe a self-evolving data pipeline that adds user interaction and MCP tool calls to the navigation data. They also describe a device-cloud setup that routes work by task state and data sensitivity, and an online reinforcement learning stage. Scaling its parallel environments from 32 to 512 added 5.2 points, and raising the step budget from 15 to 50 added 4.3. ```flow A screenshot and an instruction go in The model picks the next interface action Your agent carries the action out A new screenshot goes back to the model ``` Good to know: Scores: The authors report these figures for the MAI-UI family, and the card does not say which size each comes from. ```chart Title: Benchmark results reported by the authors MMBench GUI L2: 91.3 percent AndroidWorld: 76.7 percent ScreenSpot-Pro: 73.5 percent OSWorld-G: 70.9 percent UI-Vision: 49.2 percent MobileWorld: 41.7 percent ``` - Device and cloud: The authors say their routing raises on-device performance by 33% and cuts cloud API calls by more than 40%. - Network: The sample command sets the host to 0.0.0.0, which accepts connections from other machines on the network. - License: Apache 2.0. - Cost to run: none named. The sample runs on your own vLLM server and names no paid service. - Data it reaches: The screenshots and instructions you send to your server. The research setup can route some work to a cloud model. - Not for: The source names no forbidden uses. It is built for GUI tasks, not general chat. ## On Hugging Face, 13 November 2026 - Task: image text to text - Library: transformers - Parameters: 8.8B - Weights: about 17.5 GB in BF16; about 4.4 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 10,445 - Likes: 206 - License: apache-2.0 - Quantized versions: 7 - Fine-tunes: 1 - Tags: transformers, safetensors, qwen3_vl, image-text-to-text, conversational ## Links - Model: https://huggingface.co/Tongyi-MAI/MAI-UI-8B - Files: https://huggingface.co/Tongyi-MAI/MAI-UI-8B/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Tongyi-MAI/MAI-UI-8B ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [Tongyi-MAI/MAI-UI-8B on Hugging Face](https://huggingface.co/Tongyi-MAI/MAI-UI-8B) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | MAI-UI-8B (this page) | 10,445 | 206 | 8.8B | apache-2.0 | 2026-01-09 | | [Qwen3.8-27B](https://mindket.com/p/2f430c52-7d18-419d-8817-08ca51666598) | 6,960,395 | 19,795 | 27.8B | apache-2.0 | 2026-11-07 | | [gemma-4-31B-it](https://mindket.com/p/25c128c1-f770-475d-934f-87da192a81e2) | 6,692,367 | 4,348 | 31.3B | apache-2.0 | 2026-07-20 | | [GLM-5.3-Flash](https://mindket.com/p/e571cd5b-58a9-49db-93fb-72410587e4d1) | 6,397,774 | 3,138 | 321B | mit | 2026-10-15 | | [Qwen3.5-9B](https://mindket.com/p/acc60a90-d19e-4344-a8c1-5f984b2637b3) | 6,259,809 | 2,353 | 9.7B | apache-2.0 | 2026-03-02 | | [Qwen2.5-VL-7B-Instruct](https://mindket.com/p/156fbd08-aa88-4c47-b3d0-b73478276e66) | 5,894,471 | 1,772 | 8.3B | apache-2.0 | 2025-04-06 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-01-09 - First published: 2025-12-25 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Tongyi-MAI/MAI-UI-8B on Hugging Face](https://huggingface.co/Tongyi-MAI/MAI-UI-8B) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/b49e97ac-6be3-4e5e-a78d-98b4fac7b4e4) - [Its page on Mindket](https://mindket.com/p/b49e97ac-6be3-4e5e-a78d-98b4fac7b4e4)