--- title: Youtu-VL-4B-Instruct-GGUF canonical_url: "https://www.modelscope.cn/models/Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF" md_url: "https://www.modelscope.cn/models/Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF.md" repository: Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF last_updated: 2026-07-18 license: other pipeline_tag: image-text-to-text tasks: - image-text-to-text base_model: - tencent/Youtu-VL-4B-Instruct base_model_relation: quantized library_name: - gguf - pytorch frameworks: - pytorch downloads: 532 stars: 0 tags: - vision - vlm - gguf --- # Youtu-VL-4B-Instruct-GGUF > Youtu-VL-4B-Instruct-GGUF - Tencent-YouTu-Research 在 ModelScope 开源的模型。📃 License • 💻 Code • 🏠 Project Page • 📑 Technical Report • 📊 Benchmarks • 🚀 Getting Started Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 other 许可，基于 tencent/Youtu-VL-4B-Instruct 构建。 - **Repository**: Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF - **License**: other - **Tasks**: image-text-to-text - **Base model**: tencent/Youtu-VL-4B-Instruct - **Tags**: vision, vlm, gguf - **Downloads**: 532 - **Stars**: 0 - **Last updated**: 2026-07-18 Source: https://www.modelscope.cn/models/Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF ---
# Youtu-VL Logo [📃 License](LICENSE.txt) • [💻 Code](https://github.com/TencentCloudADP/youtu-vl) • [🏠 Project Page](https://youtu-tip.com/#llm) • [📑 Technical Report](https://arxiv.org/abs/2601.19798) • [📊 Benchmarks](#benchmarks) • [🚀 Getting Started](#quickstart)
## 🎯 Introduction **Youtu-VL** is a lightweight yet robust Vision-Language Model (VLM) built on the Youtu-LLM with 4B parameters. It pioneers Vision-Language Unified Autoregressive Supervision (VLUAS), which markedly strengthens visual perception and multimodal understanding. This enables a standard VLM to perform vision-centric tasks without task-specific additions. Across benchmarks, Youtu-VL stands out for its versatility, achieving competitive results on both vision-centric and general multimodal tasks. ## ✨ Key Features - **Comprehensive Vision-Centric Capabilities**: The model demonstrates strong, broad proficiency across classic vision-centric tasks, delivering competitive performance in visual grounding, image classification, object detection, referring segmentation, semantic segmentation, depth estimation, object counting, and human pose estimation. - **Promising Performance with High Efficiency**: Despite its compact 4B-parameter architecture, the model achieves competitive results across a wide range of general multimodal tasks, including general visual question answering (VQA), multimodal reasoning and mathematics, optical character recognition (OCR), multi-image and real-world understanding, hallucination evaluation, and GUI agent tasks.

## 🤗 Model Download | Model Name | Description | Download | | ----------- | ----------- |----------- | Youtu-VL-4B-Instruct | Visual language model of Youtu-LLM | 🤗 [Model](https://huggingface.co/tencent/Youtu-VL-4B-Instruct)| | Youtu-VL-4B-Instruct-GGUF | Visual language model of Youtu-LLM, in GGUF format | 🤗 [Model](https://huggingface.co/tencent/Youtu-VL-4B-Instruct-GGUF)| ## 🧠 Model Architecture Highlights - **Vision–Language Unified Autoregressive Supervision (VLUAS)**: Youtu-VL is built on the VLUAS paradigm to mitigate the text-dominant optimization bias in conventional VLMs, where visual signals are treated as passive conditions and fine-grained details are often dropped. Rather than using vision features only as inputs, Youtu-VL expands the text lexicon into a unified multimodal vocabulary through a learned visual codebook, turning visual signals into autoregressive supervision targets. Jointly reconstructing visual tokens and text explicitly preserves dense visual information while strengthening multimodal semantic understanding. - **Vision-Centric Prediction with a Standard Architecture (no task-specific modules)**: Youtu-VL treats image and text tokens with equivalent autoregressive status, empowering it to perform vision-centric tasks for both dense vision prediction (e.g., segmentation, depth) and text-based prediction (e.g., grounding, detection) within a standard VLM architecture, eliminating the need for task-specific additions. This design yields a versitile general-purpose VLM, allowing a single model to flexibly accommodate a wide range of vision-centric and vsion-language requirements.

## 🏆 Model Performance ### Vision-Centric Tasks

### General Multimodal Tasks

## 🚀 Quickstart This guide will help you quickly deploy and invoke the **Youtu-VL-4B-Instruct-GGUF** model using `llama.cpp`. ```bash llama-server -hf tencent/Youtu-VL-4B-Instruct-GGUF:Q8_0 \ --port 8080 \ --image-max-tokens 2048 \ --temp 0.1 \ --top-p 0.001 \ --repeat-penalty 1.05 \ -n 12280 \ --host 0.0.0.0 ``` ⚠️ **Note:** Dense prediction tasks (including Segmentation and Depth Estimation) are currently **NOT** supported in the `Youtu-VL-4B-Instruct-GGUF` version. For these capabilities, please refer to the original Transformers version: [Youtu-VL-4B-Instruct](https://huggingface.co/tencent/Youtu-VL-4B-Instruct). ## 🎉 Citation If you find our work useful in your research, please consider citing our paper: ``` @article{youtu-vl, title={Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision}, author={Tencent Youtu Lab}, year={2026}, eprint={2601.19798}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2601.19798}, } @article{youtu-llm, title={Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models}, author={Tencent Youtu Lab}, year={2025}, eprint={2512.24618}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2512.24618}, } ```