JanusCoder-8B is an open-source code intelligence foundation model built on Qwen3-8B, aiming to establish a unified visual programming interface. This model is trained on JANUSCODE-800K (the largest multimodal code corpus to date) and can handle various visual programming tasks, including data visualization, interactive web UI, and code-driven animation.

MultimodalTransformers

This project is the result of 4-bit (UINT4, SVD rank of 32) quantization of Tencent's Hunyuan Image 3.0 model. It uses the SDNQ quantization method and is specifically designed for text-to-image generation tasks.

MultimodalTransformers

UIGENT-30B-Lora-200 is a large language model fine-tuned based on Qwen3-Coder-30B-A3B-Instruct. It is specifically optimized for text generation tasks and is particularly good at handling HTML-related content. It also has various text generation capabilities.

Natural Language ProcessingTransformers

This is the quantized version of the Tesslate/UIGEN-FX-4B-Preview model, aiming to make large language models easier to deploy and use through quantization technology, realizing the concept of 'Making knowledge accessible to everyone'.

Natural Language ProcessingGguf

UIGEN-FX-4B-Preview is a UI generation model with 4 billion parameters, specifically optimized for front-end development. It can perform like a front-end engineer in 22 frameworks. This model focuses on generating semantic HTML code, with excellent layout rhythm, spacing control, and component combination capabilities, suitable for quickly generating single-file web pages.

Natural Language ProcessingTransformersEnglish

This is a GGUF format model converted from Tesslate/WEBGEN-4B-Preview, specifically designed for web page generation and UI design tasks. The model uses the Q4_K_M quantization format, which reduces the model size while maintaining good performance.

Natural Language ProcessingTransformersEnglish

This is a computer vision model fine-tuned based on Ultralytics/YOLO11, specifically designed to detect UI elements in macOS application screenshots. It is part of the Screen2AX project, dedicated to generating accessibility metadata using computer vision technology.

The quantized version of UIGEN-X-8B is committed to making knowledge accessible to the public. This model is optimized based on Tesslate/UIGEN-X-8B to provide more efficient inference performance.

Natural Language ProcessingGguf

This is a quantized model based on ONNX, which is the uint8 quantized version of Qwen/Qwen3-Embedding-0.6B. It reduces the model size while maintaining retrieval performance.

Natural Language ProcessingSentence-transformers

A quantized version based on the ByteDance-Seed/UI-TARS-1.5-7B model, using GPTQ technology for 4-bit weight quantization and 16-bit activation quantization to achieve the function of converting image-text to text, with efficient inference performance.

MultimodalSafetensors

UI-TARS-1.5-7B is a multimodal model based on advanced technology, which performs excellently in tasks such as image-text conversion. It adopts an innovative quantization method and can maintain high accuracy at extremely low bit rates.

MultimodalTransformersMultiple Languages

UI-R1-E-3B is an efficient GUI positioning model fine-tuned based on Qwen2.5-VL-3B-Instruct, specializing in visual question-answering tasks, particularly excelling at locating and identifying operational elements in user interface screenshots.

MultimodalSafetensorsEnglish

This is the GGUF quantized version of the ByteDance-Seed/UI-TARS-1.5-7B model, specifically optimized for GUI interface understanding and multimodal tasks. The model uses 4-bit quantization technology to significantly reduce the model size and memory requirements while maintaining performance.

MultimodalTransformersMultiple Languages

UIGEN-T2 is a UI generation model fine-tuned from Qwen2.5-Coder-7B-Instruct, specializing in generating HTML and Tailwind CSS code

Natural Language ProcessingGguf

UI-TARS-1.5-7B-6bit is a vision-language model converted based on the MLX format, supporting image understanding and text generation tasks.

MultimodalTransformersMultiple Languages

UI-TARS-1.5-7B-4bit is a multimodal model focused on image-text-to-text conversion tasks, supporting the English language.

MultimodalTransformersMultiple Languages

UI-TARS is the next-generation native GUI intelligent agent model, which has human-like perception, reasoning, and action capabilities, and can seamlessly interact with the graphical user interface (GUI).

MultimodalTransformersMultiple Languages

UI-TARS is the next-generation native GUI agent model with human-like perception, reasoning, and action capabilities, enabling seamless interaction with the graphical user interface (GUI).

MultimodalTransformersMultiple Languages

Raptor-X5-UIGEN is a large language model based on the Qwen 2.5 14B multimodal architecture, specializing in UI design, minimalist coding, and content-intensive development, with enhanced reasoning capabilities and structured response generation.

Natural Language ProcessingTransformersEnglish

UIGEN-T1.5 is an advanced Transformer UI generation model fine-tuned from Qwen2.5-Coder-32B-Instruct, specifically designed for generating modern and unique front-end user interfaces.

Natural Language ProcessingTransformersEnglish