Ollama

Run open models such as Gemma, Qwen, DeepSeek and gpt-oss on your own computer with one command, then use them through a local REST API, Python or JavaScript, or coding agents like Claude Code and Codex. Optional cloud models cover anything too big for your hardware.

Visit Website 185.5k
Pricing Free / cloud from $20/mo
Category Infrastructure
Local LLM Open Source CLI API Self-hosted

Founder's Verdict

"The easiest way to put an open model behind an API on your own machine. Install it, run one command, and your apps and coding agents can talk to it. Local use is free; you only pay if you want Ollama's cloud models."

Ollama

Ollama runs open models on your own computer. It’s MIT-licensed, installs on macOS, Windows and Linux, has an official Docker image, and puts every model you download behind the same local API.

What it does now

  • One command to start. ollama run gemma4:e2b downloads the model and starts a chat in your terminal.
  • A local API for your apps. Ollama serves a REST API on localhost:11434, has official Python (pip install ollama) and JavaScript (npm i ollama) libraries, and works with existing OpenAI and Anthropic clients.
  • Coding agents on open models. ollama launch claude, ollama launch codex and ollama launch opencode start Claude Code, Codex CLI or OpenCode from your project directory, running on Ollama.
  • Cloud models when your hardware runs out. Sign in and add the :cloud tag, as in gemma4:cloud, to run a model on Ollama’s servers. Ollama says it doesn’t use cloud prompts to train models, and you can turn cloud features off for local-only use.
  • A large model library, including Gemma, Qwen, DeepSeek, gpt-oss, Kimi, GLM and MiniMax, at ollama.com/search.

Plans (checked 1 Nov 2026 on ollama.com/pricing)

Running models on your own hardware is free and unlimited. The paid plans are for cloud models.

PlanPriceHighlights
Pay as you go$0Local models; cloud models billed per token; 3 concurrent requests
Pro$20/mo, or $200/yr$60 of cloud usage credits a month, larger Pro models
Max$100/mo$300 of credits a month, early access to new models, 10 concurrent requests
Team (early access)$500/moUnlimited users, $1,000 of shared credits a month, central billing, priority support
EnterpriseCustomModel access controls, spending budgets per user and API key, dedicated support

Who it’s for

  • Developers who want a local model behind a simple API, without running an inference server by hand.
  • Anyone curious about coding agents on open models, through ollama launch.
  • Teams with privacy rules that require prompts to stay on their own hardware.

Alternatives

Prefer a desktop app with a model browser? Look at LM Studio. Want the engine itself? Try llama.cpp. We compare all three in Ollama vs LM Studio vs llama.cpp.

Compared with

Ollama vs LM Studio vs llama.cpp (2026): Best Way to Run LLMs Locally Start with Ollama if you want local models behind an API for your apps and coding agents: it's MIT-licensed and a one-line install on macOS, Windows and Linux. Pick LM Studio if you'd rather work in a desktop app, especially on an Apple Silicon Mac, where it also runs MLX models. Use llama.cpp directly when you want the engine itself, with the most control over hardware backends and quantization.

Related Tools

Claude Code

Anthropic's agentic coding tool. It reads your codebase, edits files, runs commands and opens pull requests, from the terminal, VS Code, JetBrains IDEs, a desktop app, the web or Slack. Included with Claude Pro, Max, Team and Enterprise.

AgentCLI

DeepSeek

Chinese AI lab whose chat app runs on DeepSeek-V4.1-Flash, with web, mobile and desktop apps. Its models are open weights under the MIT license, and its API is among the cheapest frontier-class options.

ChatAI Assistant

Dify

★160.1k

Open-source LLM app development platform for building agentic workflows, RAG pipelines and chat apps on a visual canvas, with hundreds of models, MCP tools, observability and an API for every app. Self-host it with Docker or use Dify Cloud.

Low-codeWorkflows

llama.cpp

★133k

The open-source C/C++ engine for running LLMs and vision models locally, with a CLI, an OpenAI-compatible server with a built-in web UI, 1.5-bit to 8-bit quantization, and backends from CUDA and Metal to Vulkan and SYCL.

Local LLMOpen Source