Model Radar
AI models directory for capability-aware discovery
Focused on open models for self-hosting, research, and product development.
Model index
4
Currently filtered to open models
Model categories
Start from the workload you care about most
Model files
Open-source models
Not sure which model to inspect? Filter by openness, category, and keyword, then open profiles for capabilities, licensing, use cases, and related tools.
lpiccinelli
lpiccinelli/unidepth-v2-vitl14 · Hugging Face
UniDepth v2 (ViT-L/14) is a 0.4B-parameter PyTorch model for monocular metric depth estimation, leveraging a Vision Transformer backbone to predict scale-aware depth maps from single RGB images.
Microsoft
Phi-4
Phi-4 is a compact open-weight language model from Microsoft, optimized for structured technical tasks like coding, analysis, and research. It balances efficiency and quality, making it suitable for self-hosted or resource-constrained deployments.
DeepSeek
DeepSeek R1
DeepSeek R1 is an open-weight reasoning model developed by DeepSeek, emphasizing chain-of-thought (CoT) style reasoning for complex problem-solving. It is designed for research and deployment, with weights released under a permissive license.
Alibaba
Qwen2.5-VL 72B
Qwen2.5-VL 72B is a large multimodal AI model from Alibaba Cloud's Qwen team, designed for vision-language tasks such as image understanding, document analysis, and visual reasoning. It is an open-weight model that can be self-hosted, making it suitable for teams seeking alternatives to hosted multimodal APIs. The model excels in processing screenshots, documents, and visual data, but requires significant GPU resources for deployment.