# Ollama

## Docs

- [Environment Variables](https://mintlify.wiki/ollama/ollama/advanced/environment-variables.md): Configure Ollama server behavior with environment variables
- [GPU Configuration](https://mintlify.wiki/ollama/ollama/advanced/gpu.md): Configure GPU acceleration for NVIDIA, AMD, Apple Metal, and Vulkan devices
- [Importing Models](https://mintlify.wiki/ollama/ollama/advanced/import.md): Import models from Safetensors, GGUF, and fine-tuned adapters into Ollama
- [Model Quantization](https://mintlify.wiki/ollama/ollama/advanced/model-quantization.md): Reduce model size and memory usage with quantization techniques
- [Anthropic API Compatibility](https://mintlify.wiki/ollama/ollama/api/anthropic-compatibility.md): Use Ollama with Anthropic Claude-compatible applications
- [Authentication](https://mintlify.wiki/ollama/ollama/api/authentication.md): Authentication methods for accessing Ollama's local and cloud APIs
- [POST /api/chat](https://mintlify.wiki/ollama/ollama/api/endpoints/chat.md): Generate a chat completion with conversational context
- [POST /api/copy](https://mintlify.wiki/ollama/ollama/api/endpoints/copy.md): Copy a model
- [POST /api/create](https://mintlify.wiki/ollama/ollama/api/endpoints/create.md): Create a model from a Modelfile
- [DELETE /api/delete](https://mintlify.wiki/ollama/ollama/api/endpoints/delete.md): Delete a model and its layers
- [POST /api/embed](https://mintlify.wiki/ollama/ollama/api/endpoints/embed.md): Generate embeddings for text input
- [POST /api/embeddings](https://mintlify.wiki/ollama/ollama/api/endpoints/embeddings.md): Generate embeddings (legacy endpoint)
- [POST /api/generate](https://mintlify.wiki/ollama/ollama/api/endpoints/generate.md): Generate a completion given a prompt
- [GET /api/tags](https://mintlify.wiki/ollama/ollama/api/endpoints/list.md): List all locally available models
- [GET /api/ps](https://mintlify.wiki/ollama/ollama/api/endpoints/ps.md): List running models
- [POST /api/pull](https://mintlify.wiki/ollama/ollama/api/endpoints/pull.md): Download a model from the Ollama library
- [POST /api/push](https://mintlify.wiki/ollama/ollama/api/endpoints/push.md): Upload a model to the Ollama library
- [POST /api/show](https://mintlify.wiki/ollama/ollama/api/endpoints/show.md): Show information about a model
- [GET /api/version](https://mintlify.wiki/ollama/ollama/api/endpoints/version.md): Get Ollama version
- [Error Handling](https://mintlify.wiki/ollama/ollama/api/errors.md): Understand Ollama API error codes, status errors, and how to handle failures gracefully
- [Introduction](https://mintlify.wiki/ollama/ollama/api/introduction.md): Get started with the Ollama API to run and interact with LLMs programmatically
- [Client Libraries](https://mintlify.wiki/ollama/ollama/api/libraries.md): Official Python and JavaScript libraries for the Ollama API
- [OpenAI API Compatibility](https://mintlify.wiki/ollama/ollama/api/openai-compatibility.md): Use Ollama with OpenAI API-compatible applications
- [Streaming Responses](https://mintlify.wiki/ollama/ollama/api/streaming.md): Understand how Ollama uses server-sent events to stream model responses in real-time
- [Usage Metrics](https://mintlify.wiki/ollama/ollama/api/usage.md): Track token usage, timing, and performance metrics for Ollama API requests
- [ollama cp](https://mintlify.wiki/ollama/ollama/cli/cp.md): Copy a model to create a new model name or backup
- [ollama create](https://mintlify.wiki/ollama/ollama/cli/create.md): Create a custom model from a Modelfile
- [ollama launch](https://mintlify.wiki/ollama/ollama/cli/launch.md): Launch the Ollama menu or integrations with editor tools
- [ollama list](https://mintlify.wiki/ollama/ollama/cli/list.md): List all models in your local library
- [CLI Overview](https://mintlify.wiki/ollama/ollama/cli/overview.md): Complete reference for the Ollama command-line interface
- [ollama ps](https://mintlify.wiki/ollama/ollama/cli/ps.md): List currently running models
- [ollama pull](https://mintlify.wiki/ollama/ollama/cli/pull.md): Download a model from a registry
- [ollama push](https://mintlify.wiki/ollama/ollama/cli/push.md): Upload a model to a registry
- [ollama rm](https://mintlify.wiki/ollama/ollama/cli/rm.md): Remove one or more models from your local library
- [ollama run](https://mintlify.wiki/ollama/ollama/cli/run.md): Run a model interactively or with a prompt
- [ollama serve](https://mintlify.wiki/ollama/ollama/cli/serve.md): Start the Ollama server
- [ollama show](https://mintlify.wiki/ollama/ollama/cli/show.md): Display detailed information about a model
- [ollama signin](https://mintlify.wiki/ollama/ollama/cli/signin.md): Sign in to ollama.com to access cloud models and push models
- [ollama signout](https://mintlify.wiki/ollama/ollama/cli/signout.md): Sign out from ollama.com and revoke authentication
- [ollama stop](https://mintlify.wiki/ollama/ollama/cli/stop.md): Stop a running model and unload it from memory
- [Context and Memory](https://mintlify.wiki/ollama/ollama/context-and-memory.md)
- [Contributing](https://mintlify.wiki/ollama/ollama/contributing.md): Learn how to contribute to the Ollama project
- [FAQ](https://mintlify.wiki/ollama/ollama/faq.md): Frequently asked questions about Ollama
- [Chat](https://mintlify.wiki/ollama/ollama/features/chat.md): Multi-turn conversations with models that maintain context and history.
- [Embeddings](https://mintlify.wiki/ollama/ollama/features/embeddings.md): Generate text embeddings for semantic search, retrieval, and RAG.
- [Streaming](https://mintlify.wiki/ollama/ollama/features/streaming.md): Stream model responses in real-time for better user experience.
- [Structured Outputs](https://mintlify.wiki/ollama/ollama/features/structured-outputs.md): Enforce JSON schemas on model responses for reliable data extraction.
- [Thinking](https://mintlify.wiki/ollama/ollama/features/thinking.md): Access model reasoning traces for transparency and debugging.
- [Tool Calling](https://mintlify.wiki/ollama/ollama/features/tool-calling.md): Enable models to invoke functions and incorporate results into responses.
- [Vision](https://mintlify.wiki/ollama/ollama/features/vision.md): Use multimodal models to analyze images and answer questions about visual content.
- [Web Search](https://mintlify.wiki/ollama/ollama/features/web-search.md): Augment models with real-time web information to reduce hallucinations.
- [Installation](https://mintlify.wiki/ollama/ollama/installation.md): Install Ollama on macOS, Windows, Linux, or Docker
- [Claude Code](https://mintlify.wiki/ollama/ollama/integrations/claude-code.md): Anthropic's agentic coding tool with subagent support
- [Codex](https://mintlify.wiki/ollama/ollama/integrations/codex.md): OpenAI's open-source coding agent for terminal workflows
- [Droid](https://mintlify.wiki/ollama/ollama/integrations/droid.md): Factory's AI coding agent across terminal and IDEs
- [IDE Extensions](https://mintlify.wiki/ollama/ollama/integrations/ide-extensions.md): Native Ollama integrations for popular development environments
- [Libraries & SDKs](https://mintlify.wiki/ollama/ollama/integrations/libraries.md): Official and community libraries for integrating Ollama into your applications
- [OpenClaw](https://mintlify.wiki/ollama/ollama/integrations/openclaw.md): Personal AI assistant that bridges messaging apps to local and cloud models
- [OpenCode](https://mintlify.wiki/ollama/ollama/integrations/opencode.md): Open-source AI coding assistant for your terminal
- [Integrations Overview](https://mintlify.wiki/ollama/ollama/integrations/overview.md): Launch AI agents and connect to coding tools with Ollama
- [Welcome to Ollama](https://mintlify.wiki/ollama/ollama/introduction.md): Run large language models locally with ease
- [Modelfile](https://mintlify.wiki/ollama/ollama/modelfile.md)
- [Models](https://mintlify.wiki/ollama/ollama/models.md)
- [Cloud](https://mintlify.wiki/ollama/ollama/platforms/cloud.md): Run large language models without a GPU using Ollama's cloud service
- [Docker](https://mintlify.wiki/ollama/ollama/platforms/docker.md): Run Ollama in Docker containers with support for CPU, NVIDIA GPU, AMD GPU, and Vulkan
- [Linux](https://mintlify.wiki/ollama/ollama/platforms/linux.md): Install and configure Ollama on Linux with support for NVIDIA, AMD, and CPU inference
- [macOS](https://mintlify.wiki/ollama/ollama/platforms/macos.md): Install and run Ollama on macOS with native Apple Silicon and Intel support
- [Windows](https://mintlify.wiki/ollama/ollama/platforms/windows.md): Install and run Ollama on Windows with NVIDIA and AMD Radeon GPU support
- [Quickstart Guide](https://mintlify.wiki/ollama/ollama/quickstart.md): Get up and running with Ollama in minutes
- [Troubleshooting](https://mintlify.wiki/ollama/ollama/troubleshooting.md): How to troubleshoot issues encountered with Ollama