AI models directory for capability-aware discovery

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.

Qwen/Qwen3-8B is an 8-billion parameter large language model developed by Alibaba Cloud's Qwen team, available on Hugging Face under the Apache 2.0 license. It is designed for advanced text generation, conversational AI, and complex reasoning tasks, featuring support for tool use and long-context understanding.

MiniMax M3 is a frontier open-weight multimodal large language model developed by MiniMax. It distinguishes itself by combining state-of-the-art coding and agentic capabilities with a massive 1-million-token context window and native multimodal understanding. Built on the proprietary MiniMax Sparse Attention (MSA) architecture, M3 is designed for complex, long-horizon tasks such as autonomous software engineering, multi-step tool use, and deep analysis of long documents or videos.

Gemini Spark is a high-efficiency variant within Google DeepMind's Gemini family, designed specifically for low-latency, cost-effective applications. It leverages optimized inference techniques to deliver rapid responses suitable for real-time interactions, such as conversational agents and streaming services, while maintaining strong performance on standard benchmarks.

Claude Sonnet is a hybrid reasoning AI model family developed by Anthropic, designed for high-volume production workloads, advanced coding, and autonomous agent operations. The latest iteration, Claude Sonnet 5, features a 1 million token context window, optimized for real-time interactions and complex multi-step tasks. It balances frontier-level performance with cost-efficiency, offering native availability on the Claude Platform, AWS, Google Cloud, and Microsoft Foundry.

GPT-5.6 is not a verified public AI model. As of the current date, OpenAI has not released a model named 'GPT-5.6', nor has it published an official index page at the provided URL. The entity described appears to be a hallucination, a mislabeled entry, or a reference to a non-existent or future product. Consequently, no technical specifications, capabilities, or deployment details can be provided.

T5-small is a compact, multilingual encoder-decoder transformer model developed by Google and hosted on Hugging Face. Licensed under Apache 2.0, it supports text-to-text generation tasks such as translation, summarization, and question answering across multiple languages including English, French, German, and Romanian. It is optimized for low-latency inference and efficient deployment on various hardware backends.

Tiangong AI is a comprehensive artificial intelligence platform developed by Kunlun Tech, designed primarily for Chinese-speaking users. It functions as an integrated ecosystem combining advanced AI-powered search capabilities with robust creative content generation tools. Unlike standalone large language models that focus solely on text completion or chat, Tiangong AI positions itself as a productivity suite that bridges the gap between information retrieval and content production. By leveraging large language models (LLMs) under the hood, it allows users to perform complex searches, synthesize real-time web data, and immediately transform those findings into structured articles, reports, or creative writing. The platform is accessible via web and mobile applications, emphasizing ease of use for professionals, students, and content creators operating within the Chinese digital landscape.

360 AI Search is a proprietary, LLM-integrated search service developed by Qihoo 360. It merges traditional web indexing with generative AI to provide direct, conversational answers while citing source URLs. Optimized primarily for the Chinese market, it operates within the 360 ecosystem, including the 360 Browser, and is not available as an open-source model or downloadable package.

GPT-4.1 is a hosted large language model from OpenAI optimized for practical software, agent, and business workflows. It is designed for general reasoning, coding assistance, and research tasks, with an API-first deployment model that simplifies integration but ties operations to OpenAI's infrastructure.

Qwen/Qwen3-0.6B is a lightweight, open-source large language model developed by Alibaba Cloud's Qwen team. Released under the permissive Apache 2.0 license, this 0.6-billion-parameter model is designed for high-efficiency deployment on consumer-grade hardware, including CPUs and low-end GPUs. It features a 32,768-token context window, multilingual capabilities, and native support for tool-use and function calling, making it an ideal candidate for edge computing, real-time chatbots, and resource-constrained environments.

LLaVA (Large Language and Vision Assistant) is an open-source, end-to-end trained multimodal model that combines a vision encoder with a large language model (Vicuna) to enable visual understanding and reasoning. Developed by researchers from Microsoft, the University of Wisconsin-Madison, and Columbia University, LLaVA allows users to interact with images through natural language, supporting tasks such as visual question answering, image captioning, and complex visual reasoning. The latest iteration, LLaVA 1.6, introduces significant improvements in input resolution, visual instruction tuning, and logical reasoning capabilities. It is widely accessible for local deployment via Ollama, offering privacy, offline functionality, and flexible hardware requirements across various model sizes.

BAAI/bge-small-en-v1.5 is a lightweight, high-performance sentence embedding model developed by the Beijing Academy of Artificial Intelligence (BAAI). Based on the BERT architecture with approximately 33 million parameters, it generates 384-dimensional vector representations optimized for English text. It is widely used for semantic search, retrieval-augmented generation (RAG), and clustering tasks, offering a balance between computational efficiency and accuracy under the permissive MIT License.

openai/clip-vit-base-patch32 is a foundational multimodal AI model developed by OpenAI and hosted on Hugging Face. It implements the Contrastive Language-Image Pre-training (CLIP) architecture, specifically utilizing a Vision Transformer (ViT-B/32) encoder paired with a text transformer. This model is designed to learn visual concepts directly from natural language supervision, enabling powerful zero-shot image classification and cross-modal retrieval capabilities without the need for task-specific training data.

timm/mobilenetv3_small_100.lamb_in1k is a highly efficient image classification model from the MobileNetV3 family, optimized for resource-constrained environments such as mobile devices and IoT hardware. Pretrained on ImageNet-1k using the LAMB optimizer, it offers a balance of accuracy and speed with approximately 2.5 million parameters.

BGE Reranker v2 M3 is a cross-encoder reranking model by BAAI, built on XLM-RoBERTa, supporting 100+ languages. It outputs relevance scores for query-document pairs, achieving state-of-the-art results on multilingual retrieval benchmarks. Licensed under Apache 2.0, it has over 16 million downloads and is deployable via Hugging Face, Sentence-Transformers, and Text Embeddings Inference.

nomic-embed-text is a high-performance, open-source text embedding model developed by Nomic AI. Designed for local deployment via Ollama, it supports a 2,048-token context window and generates 768-dimensional vectors. The model is licensed under Apache 2.0 and is optimized for semantic search, RAG pipelines, and document clustering, offering a privacy-preserving alternative to cloud-based embedding services.

Mistral is a 7.3 billion parameter open-weight language model developed by Mistral AI. Released under the permissive Apache 2.0 license, it is designed for high efficiency and strong performance on consumer-grade hardware. The model supports instruction following, coding, and multilingual tasks, with recent updates (v0.3) adding native function calling capabilities. It is widely accessible via the Ollama platform for local deployment.

o3-mini is a compact reasoning model from OpenAI designed for efficient technical tasks, offering stronger reasoning than GPT-3.5 in a lighter package than GPT-4. It is typically accessed via hosted APIs, balancing cost and latency for coding, analysis, and research use cases.

sentence-transformers/all-mpnet-base-v2 is a high-performance, English-only sentence embedding model fine-tuned from Microsoft’s MPNet base architecture. It maps text into a 768-dimensional dense vector space, widely recognized for its state-of-the-art performance on semantic textual similarity (STS) and retrieval benchmarks. Licensed under Apache 2.0, it serves as a foundational component for semantic search, clustering, and information retrieval systems.