spb/tools-spboucher-ai
Public
1{2 "slug": "ollama",3 "name": "Ollama",4 "aliases": [],5 "vendor": { "name": "Ollama", "slug": "ollama", "website": "https://ollama.com" },6 "homepage_url": "https://ollama.com/",7 "docs_url": "https://docs.ollama.com/",8 "repo_url": "https://github.com/ollama/ollama",9 "pricing_url": "https://ollama.com/pricing",10 "license_url": "https://github.com/ollama/ollama/blob/main/LICENSE",11 "product_type": "application",12 "product_status": "active",13 "summary": "Open-source runtime and model manager for running open-weight LLMs locally on macOS, Windows and Linux, with a REST API, OpenAI- and Anthropic-compatible endpoints and optional cloud models",14 "description": "Ollama is an MIT-licensed runtime for running open-weight language models on your own machine. A single install on macOS, Windows or Linux (or the official Docker image) provides a background server, a CLI (`ollama run`, `ollama pull`, `ollama launch`) and, on desktop platforms, a chat app. Models are fetched from the Ollama library by name and stored as layered blobs; a Modelfile lets you derive variants with a different system prompt, parameters or adapter. Inference is built on llama.cpp's GGML engine, with Metal acceleration on Apple Silicon and CUDA or ROCm on discrete GPUs.\n\nThe server listens on port 11434 and exposes Ollama's native REST API plus OpenAI- and Anthropic-compatible endpoints, which is why many editors, agents and frameworks treat Ollama as a drop-in local backend. Official Python and JavaScript SDKs cover chat, generation, embeddings and tool calling, and `ollama launch` starts integrations such as Claude Code or OpenClaw against a local model. Since 2025 the company also sells cloud-hosted models through the same CLI and API, on pay-as-you-go, Pro, Max, Team and Enterprise plans, while local inference remains free and unmetered.\n\nIn a research or small-team setting Ollama is the quickest way to serve an embedding or chat model on a Mac Studio for private workloads. Its limits are those of a single-node consumer runtime: throughput and concurrency are far below vLLM on server GPUs, model choice is restricted to the GGUF conversions in the library or ones you import, and quantized models trade some quality for memory. Behavior on headless macOS machines under launchd also needs care, since the desktop app and the CLI server are separate processes.",15 "capabilities": ["One-command model download and execution from a curated library", "Native REST API plus OpenAI- and Anthropic-compatible endpoints on port 11434", "Modelfile for custom system prompts, parameters and adapters", "Official Python and JavaScript SDKs with tool calling and embeddings", "Metal, CUDA and ROCm acceleration; CPU fallback", "Desktop app on macOS and Windows; Docker image for servers", "Optional cloud models billed per token through the same interface", "`ollama launch` to connect coding agents to local models"],16 "workflows": ["Serve a quantized chat model on a Mac for a private assistant", "Generate embeddings locally for a vector index", "Point an OpenAI-compatible client at localhost to test without API costs", "Mix local and cloud models from one CLI"],17 "advantages": ["Simple installation and model management", "Broad client ecosystem through OpenAI-compatible API", "MIT license, local use free and unmetered", "Works well on Apple Silicon unified memory"],18 "limitations": ["Single-node, modest concurrency compared with server engines", "Only GGUF-packaged models unless imported manually", "Cloud models are proprietary hosted services with separate terms", "Separate desktop app and CLI server processes can confuse headless setups"],19 "prerequisites": ["macOS, Windows or Linux with enough RAM or VRAM for the chosen model", "Optional: NVIDIA or AMD GPU drivers"],20 "audiences": ["Developers prototyping LLM features offline", "Researchers running private inference on workstations", "Home-lab and small-team operators"],21 "alternatives": ["llama-cpp", "lm-studio", "vllm", "mlx-lm"],22 "comparison_notes": "llama.cpp is the underlying engine; using it directly gives more control and the newest model support at the cost of manual builds and model files. LM Studio offers a richer GUI and MLX support on Apple Silicon but is proprietary. vLLM targets high-throughput GPU serving with continuous batching and is not aimed at laptops. mlx-lm is Apple's own path for Apple Silicon and avoids GGUF conversion but has a smaller client ecosystem.",23 "categories": [{ "slug": "local-inference", "primary": true }, { "slug": "apple-silicon-ml", "label": "Metal-accelerated local models on Macs" }],24 "tags": ["llm", "self-hosted", "open-source", "cli", "api", "macos", "apple-silicon", "embeddings"],25 "use_cases": ["run-local-models", "serve-models", "build-agents"],26 "operating_systems": ["macos", "windows", "linux"],27 "execution_modes": ["local", "self-hosted", "cloud"],28 "interfaces": ["cli", "api", "sdk", "desktop"],29 "deployment_models": ["desktop", "on-premises", "saas"],30 "integrations": ["llama.cpp", "Claude Code", "Open WebUI", "LangChain", "LlamaIndex", "LiteLLM", "Continue", "Docker"],31 "data_formats": ["GGUF", "Safetensors (import)", "Modelfile", "JSON"],32 "languages": ["Go", "Python", "JavaScript"],33 "source_model": "open-source",34 "license_spdx": "MIT",35 "pricing_model": ["open-source", "free", "usage-based", "paid", "enterprise"],36 "pricing_checked_at": "2026-11-02",37 "self_hostable": true,38 "sources": [39 { "url": "https://ollama.com/", "type": "official_site", "title": "Ollama", "supports": ["name", "summary"], "checked_at": "2026-11-02" },40 { "url": "https://docs.ollama.com/", "type": "official_docs", "title": "Ollama documentation", "supports": ["capabilities", "interfaces", "integrations"], "checked_at": "2026-11-02" },41 { "url": "https://github.com/ollama/ollama", "type": "repository", "title": "ollama/ollama", "supports": ["operating_systems", "languages", "capabilities"], "checked_at": "2026-11-02" },42 { "url": "https://github.com/ollama/ollama/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" },43 { "url": "https://ollama.com/pricing", "type": "pricing_page", "supports": ["pricing_model"], "checked_at": "2026-11-02", "note": "Pay as you go, Pro, Max, Team, Enterprise for cloud models; local use unlimited" }44 ],45 "confidence": "high",46 "discovery_method": "editorial-research",47 "depth": "deep",48 "editorial_status": "reviewed",49 "visibility": "public",50 "featured": true,51 "author": "batch-A"52}53