Directory
Published directory entries matching your search.
Ludwig is a low-code framework for building custom large language models, neural networks, and other AI models. The project's repository includes introductory documentation, release notes for version 0.16, installation guides, quick start materials, and resources for instruction fine-tuning of LLMs.
MathArena evaluates large language models on uncontaminated math benchmarks. It presents model analysis across competitions such as ArXivLean, BrokenArXiv, ArXivMath, Visual Math, Final-Answer Comps, Proof-Based Comps and Project Euler. A competition is selected to load tables and a leaderboard, and clicking a cell shows the raw model output.
Meituan Long Cat provides machine-learning models, research, training resources, or evaluation tools.
A Julia package for fitting (statistical) mixed-effects models.
ML Resources supports machine learning models, deployment, inspection, datasets, or AI development workflows.
MMDeploy is documented at version 1.3.1 and covers getting started, converting, running, evaluating and quantizing models, building from source or Docker image, and SDK usage. Its backend support pages describe ncnn, ONNX Runtime, OpenVINO, PPLNN, SNPE, TensorRT, TorchScript, RKNN, TVM and Core ML, and its codebase support covers several OpenMMLab projects.
NuExtract 2.0 is a document information extraction model developed by NuMind. NuMind builds frontier multimodal large language models that convert documents into structured JSON and clean Markdown, available via SaaS or private enterprise deployment. The models are specialized for document extraction and deployed in industries including insurance, banking, and healthcare; for example, AXA increased its extraction accuracy from 30% to 97% after switching to NuExtract.
Odysseus is a self-hosted AI workspace for running language models on one's own hardware. It offers chat, autonomous agents, tools and MCP connections, model serving, an email assistant, deep research, model comparison and persistent memory. The project is described as local-first and privacy-first, with no telemetry.
Ollama is a tool for running and building with open AI models locally or in the cloud on macOS, Windows and Linux. Its pricing page lists Free, Pro, Max, Team and Enterprise subscription plans, with paid plans including usage credits and cloud model access. The Free plan includes running models locally and starter usage credits.
Open WebUI is a self-hosted AI interface for running AI on the user's own hardware. It connects to local or cloud models including Ollama, OpenAI, Anthropic, or compatible services, and can be extended with Python. The project offers community-shared prompts, models, tools, and functions, and lists deployment options including on-premises or air-gapped setups. Installation can be done with a pip command.
Evals is a framework for evaluating large language models and systems built using LLMs. It offers an existing registry of evals to test different dimensions of OpenAI models and the ability to write custom evals. It is available as an open-source registry of benchmarks. Evals require an OpenAI API key.
OpenLLM is a project from BentoML for running open-source LLMs or custom models as OpenAI-compatible APIs with a single command. It includes a built-in chat UI, inference backends, and a workflow for cloud deployment with Docker, Kubernetes, and BentoCloud, and it does not store model weights. A Hugging Face token is required for gated models.
OpenLM Arena is a leaderboard site that ranks large language models. It bases rankings on three benchmarks: an agent-driven battle platform with Bradley-Terry Elo ratings from LLM-as-a-judge votes, a Model Intelligence Index, and the ARC-AGI-2 general intelligence benchmark. The page lists models with Elo, coding, vision, MII and ARC-AGI figures alongside organization and license.
OpenML supports machine learning models, deployment, inspection, datasets, or AI development workflows.
OpenRouter hosts an LLM ranking and AI leaderboard that ranks large language models by real-world usage metrics, specifically the volume of tokens processed through the OpenRouter API. It is intended to show which AI models are most widely used by developers.
Jan is an open source alternative to ChatGPT that runs offline on the user's computer, according to the repository description. It provides local AI models downloaded and run with an OpenAI-compatible local server at localhost:1337 and supports connecting to cloud GPT and Claude models according to the README features list.
Optimum-TPU is a Hugging Face project providing Google TPU optimizations for transformers models, aiming to ease training and inference on TPUs. It supports text generation models including Gemma, Llama2, Llama3 and Mistral, and includes a text-generation-inference backend. The repository was archived in January 2026 and is read-only, with the project in maintenance mode.
oumi-ai/oumi is a publicly available GitHub repository that provides tools and workflows for fine-tuning, evaluating, and deploying open-weight large language models, with support for models such as Qwen and Gemma.
pkuseg is a Python toolkit for multi-domain Chinese word segmentation, based on a 2019 paper. It provides pretrained models for news, web, medicine, tourism, and mixed domains, and supports user-trained models and part-of-speech tagging. It is distributed under the MIT license.
Poolside AI provides machine-learning models, research, training resources, or evaluation tools.
Qwen is an AI project whose site lists models including Qwen3Guard, a safety guardrail model built on Qwen3 foundation models for detecting risk in prompts and responses. It also lists Qwen-Image-Edit, an image editing version of a 20B Qwen-Image model, and Qwen-MT, a translation model via Qwen API supporting 92 languages.
A blog article about red-teaming large language models, described as a form of evaluation that elicits model vulnerabilities that might lead to undesirable behaviors. It discusses undesirable behaviors such as revealing personal information, misinformation, bias, hatefulness and toxic content, and compares red-teaming with adversarial attacks. It notes that red-teaming prompts look like regular natural language prompts.
RunThisLLM is a website that provides hardware requirements for running local AI models. It lists over 295 models with full build specifications, performance estimates, and benchmarks. It also offers a Chrome extension and a custom machine building service.
Sarvam provides machine-learning models, research, training resources, or evaluation tools.
