--- title: UGround-V1-2B-bf16 canonical_url: "https://www.modelscope.cn/models/mlx-community/UGround-V1-2B-bf16" md_url: "https://www.modelscope.cn/models/mlx-community/UGround-V1-2B-bf16.md" repository: mlx-community/UGround-V1-2B-bf16 last_updated: 2026-03-22 license: apache-2.0 pipeline_tag: image-text-to-text tasks: - image-text-to-text model_type: - qwen2_vl architectures: - Qwen2VLForConditionalGeneration base_model: - osunlp/UGround-V1-2B base_model_relation: finetune parameters: 2.2B tensor_type: - BF16 library_name: - mlx - safetensors - pytorch frameworks: - pytorch language: - en inference_backends: - "deploy_task vlm/text/emb" - "lmdeploy 0.9.1" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 14 stars: 0 tags: - mlx - mlx-vlm - safetensors - apple-silicon - conversational - gui - vision-language-model - qwen2_vl - uground - grounding - computer-use - agent - 2b - bf16 --- # UGround-V1-2B-bf16 > UGround-V1-2B-bf16 - mlx-community 在 ModelScope 开源的模型。This is an MLX conversion of osunlp/UGround-V1-2B, optimized for Apple Silicon. mlx-community/UGround-V1-2B-bf16 是 ModelScope 魔搭社区上的 2.2B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 osunlp/UGround-V1-2B 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。 - **Repository**: mlx-community/UGround-V1-2B-bf16 - **License**: apache-2.0 - **Tasks**: image-text-to-text - **Parameters**: 2.2B - **Base model**: osunlp/UGround-V1-2B - **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2 - **Tags**: mlx, mlx-vlm, safetensors, apple-silicon, conversational, gui, vision-language-model, qwen2_vl, uground, grounding, computer-use, agent, 2b, bf16 - **Downloads**: 14 - **Stars**: 0 - **Last updated**: 2026-03-22 Source: https://www.modelscope.cn/models/mlx-community/UGround-V1-2B-bf16 --- # UGround-V1-2B bf16 This is an MLX conversion of [osunlp/UGround-V1-2B](https://huggingface.co/osunlp/UGround-V1-2B), optimized for Apple Silicon. UGround is a GUI visual grounding model built on Qwen2-VL and framed upstream around point-based grounding for screen elements. This refreshed MLX artifact is intended to replace the older stale `mlx-community/UGround-V1-2B` conversion as the structurally trustworthy Track E reference row. This MLX artifact was converted with `mlx-vlm`, structurally triaged locally, and checked for basic runtime viability with direct `mlx_vlm` probes. ## Conversion Details | Field | Value | |---|---| | Upstream model | `osunlp/UGround-V1-2B` | | Artifact type | `bf16 MLX conversion` | | Conversion tool | `mlx_vlm.convert` via `mlx-vlm 0.3.12` | | Python | `3.11.14` | | MLX | `0.31.0` | | Validation backend | `vllm-mlx (phase/p1 @ 48b51ed)` | | Quantization | `bf16` | | Group size | `n/a` | | Quantization mode | `n/a` | | Artifact size | `4.5G` | | Template repair | `tokenizer_config.json["chat_template"]` was re-injected from `chat_template.jinja` after conversion | Additional notes: - Root-level `processor_config.json` is present. This is the key structural fix relative to the older stale `mlx-community/UGround-V1-2B` artifact. - `chat_template.jinja`, `chat_template.json["chat_template"]`, and `tokenizer_config.json["chat_template"]` were verified to match exactly after repair. - Local multimodal detection now passes on this refreshed artifact. ## Validation This artifact passed local structural triage in this workspace: - root packaging / multimodal structure: `PASS` - tokenizer-visible template repair: `PASS` - safetensors and index structure: `PASS` - minimum runtime viability: `PASS with caution` Local notes: - source posture: fresh-source conversion from `osunlp/UGround-V1-2B` - root structure: corrected relative to the older stale public MLX artifact - structural triage verdict: `triage-pass` - quantization status: still blocked pending stronger semantic evidence Important limitation: - the refreshed artifact is structurally sound, but the first local grounding/classification probes were weak - this repo should be treated as the authoritative fresh MLX reference artifact for Track E, not yet as a recommended winning row for GUI grounding ## Usage ### Install ```bash pip install -U mlx-vlm ``` ### CLI ```bash python -m mlx_vlm.generate \ --model mlx-community/UGround-V1-2B-bf16 \ --image path/to/image.png \ --prompt "Your task is to help the user identify the precise coordinates (x, y) of a specific area or element on the screen based on a description. Your response should be a single string (x, y) corresponding to the point of interest on a 0-1000 grid. Description: API Host input field. Answer:" \ --max-tokens 64 \ --temperature 0.0 ``` ### Python ```python from mlx_vlm import load, generate model, processor = load("mlx-community/UGround-V1-2B-bf16") result = generate( model, processor, prompt=( "Your task is to help the user identify the precise coordinates (x, y) " "of a specific area or element on the screen based on a description. " "Your response should be a single string (x, y) corresponding to the " "point of interest on a 0-1000 grid. Description: API Host input field. " "Answer:" ), image="path/to/image.png", max_tokens=64, temp=0.0, ) print(result.text) ``` ## Links - Upstream model: [osunlp/UGround-V1-2B](https://huggingface.co/osunlp/UGround-V1-2B) - Homepage: [osu-nlp-group.github.io/UGround](https://osu-nlp-group.github.io/UGround/) - Repository: [OSU-NLP-Group/UGround](https://github.com/OSU-NLP-Group/UGround) - Paper: [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://arxiv.org/abs/2410.05243) - Original stale MLX artifact: [mlx-community/UGround-V1-2B](https://huggingface.co/mlx-community/UGround-V1-2B) - MLX framework: [ml-explore/mlx](https://github.com/ml-explore/mlx) - mlx-vlm: [Blaizzy/mlx-vlm](https://github.com/Blaizzy/mlx-vlm) ## Other Quantizations Not published from this Track E lane: - `6bit` not authorized - `4bit` not authorized If a later operator decision reopens quantization, those rows should be derived from this refreshed `bf16` artifact rather than from the stale public MLX repo. ## Notes and Limitations - This card reports local MLX conversion and structural-triage results only. - Upstream benchmark tables belong to the original UGround family and were not re-run here. - The older `mlx-community/UGround-V1-2B` artifact should be treated as stale comparison context, not as the authoritative root for later quantization work. - First local semantic probes were weak enough that quantization remained blocked after triage. ## Citation If you use this MLX conversion, please also cite the original UGround work: ```bibtex @article{gou2024uground, title={Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents}, author={Boyu Gou and Ruohan Wang and Boyuan Zheng and Yanan Xie and Cheng Chang and Yiheng Shu and Huan Sun and Yu Su}, journal={arXiv preprint arXiv:2410.05243}, year={2024}, url={https://arxiv.org/abs/2410.05243}, } ``` ## License This repo follows the upstream model license: Apache 2.0. See the upstream model card for the authoritative license details: [osunlp/UGround-V1-2B](https://huggingface.co/osunlp/UGround-V1-2B).