Ollama
The simplest way to download and run open-weight LLMs locally behind an API.
Quick answer
Ollama is the simplest way to download and run open-weight LLMs locally behind an API, listed under Local model runtimes. A typical small-business use: keep sensitive prompts on your own hardware instead of a cloud API. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: MIT, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is Ollama?
Ollama pulls and runs open models such as Llama, Qwen, Gemma and Mistral with one command and serves them on a local HTTP API that many other tools in this directory support. It runs on CPU or on NVIDIA, AMD and Apple GPUs.
Where it fits in a 10–200 person business
- Keep sensitive prompts on your own hardware instead of a cloud API
- Local model back-end for Open WebUI, AnythingLLM, Dify or n8n
- Offline or air-gapped AI for regulated work
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Ollama? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed. Individual models have their own licenses. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does Ollama need?
The project does not publish a minimum CPU/RAM figure, so we leave it blank rather than guess.
GPU: NVIDIA GPUs need compute capability 5.0+ and driver 550+ (570+ for compute capability 5.0–6.2). CPU-only also works.
Memory needs depend on the model you load, not on Ollama itself.
Source: docs.ollama.com/gpu
How much does it cost to host Ollama per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy Ollama
Method: Docker (or install script)
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
# Linux native: curl -fsSL https://ollama.com/install.sh | shFrom the official instructions: docs.ollama.com/docker. Always check the source for the current version before you run it.
Known gotchas when self-hosting Ollama
Alternatives in Local model runtimes
- vLLM High-throughput LLM inference server for GPUs with an OpenAI-compatible API. Compare Ollama vs vLLM
- LocalAI OpenAI-compatible API for LLMs, vision, voice and images on any hardware. Compare LocalAI vs Ollama
Ollama FAQ
How much RAM does Ollama need?
Ollama does not publish an official RAM figure, so we do not state one. Memory needs depend on the model you load, not on Ollama itself.
Does Ollama need a GPU?
NVIDIA GPUs need compute capability 5.0+ and driver 550+ (570+ for compute capability 5.0–6.2). CPU-only also works.
How much does it cost to self-host Ollama?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is Ollama free for commercial use?
Ollama is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed. Individual models have their own licenses. This is a summary, not legal advice.
What are common problems when self-hosting Ollama?
Older NVIDIA cards (compute capability 5.0–6.2) need driver 570 or newer. With the Vulkan backend, Ollama needs root or the cap_perfmon capability (sudo setcap cap_perfmon+ep /usr/local/bin/ollama) to read free VRAM; otherwise it schedules models using approximate sizes.
Is Ollama still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v0.40.8 (Oct 21, 2026). Checked Oct 22, 2026.
How do I install Ollama?
The official method is Docker (or install script). The exact commands are in the "How to deploy" section above and in the official instructions: https://docs.ollama.com/docker
What are self-hosted alternatives to Ollama?
Other apps in Local model runtimes: vLLM, LocalAI.
Sources
- GitHub repository: github.com/ollama/ollama
- Official documentation, Deploy instructions: docs.ollama.com/docker
- License text: github.com/ollama/ollama/blob/main/LICENSE
- Hardware requirements, Gotcha 1, Gotcha 2: docs.ollama.com/gpu
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.