Tabby
Self-hosted AI coding assistant (Copilot alternative) for your team.
Quick answer
Tabby is a self-hosted AI coding assistant (Copilot alternative) for your team, listed under Coding assistants. A typical small-business use: code completion for a dev team that cannot send source code to a cloud service. It needs a GPU server; we do not estimate that cost because GPU prices vary too much by card and provider. License: Apache-2.0 (ee directory under a separate license), 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 Tabby?
Tabby serves code completion and chat models from your own GPU server, with IDE extensions for VS Code, JetBrains and others. It can index your repositories for context and needs no external database or cloud service.
Where it fits in a 10–200 person business
- Code completion for a dev team that cannot send source code to a cloud service
- Chat about internal repositories with repository context
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Tabby? (license)
| License | Apache-2.0 (ee directory under a separate license) |
|---|---|
| Type | Open core: Core is MIT/Apache; enterprise folders need a paid license. |
| Internal business use | Allowed under the license text |
| What to watch | Everything outside the "ee/" directory is Apache-2.0. The ee/ directory has its own license. |
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 Tabby need?
The project does not publish a minimum CPU/RAM figure, so we leave it blank rather than guess.
GPU: NVIDIA GPU recommended. CodeLlama-7B in int8 needs about 8 GB VRAM. int8 needs compute capability 7.0+ (or 6.1), float16 7.0+, bfloat16 8.0+.
VRAM depends on the models you choose.
Source: tabby.tabbyml.com/docs/faq/
How much does it cost to host Tabby per month?
Needs a GPU server for practical use. Not estimated, because GPU prices vary too much by card and provider.
How to deploy Tabby
Method: Docker (CUDA)
docker run -d --name tabby --gpus all -p 8080:8080 \
-v $HOME/.tabby:/data registry.tabbyml.com/tabbyml/tabby \
serve --model StarCoder-1B --chat-model Qwen2-1.5B-Instruct --device cudaFrom the official instructions: tabby.tabbyml.com/docs/quick-start/installation/docker/. Always check the source for the current version before you run it.
Known gotchas when self-hosting Tabby
Tabby FAQ
How much RAM does Tabby need?
Tabby does not publish an official RAM figure, so we do not state one. VRAM depends on the models you choose.
Does Tabby need a GPU?
For practical use, yes. NVIDIA GPU recommended. CodeLlama-7B in int8 needs about 8 GB VRAM. int8 needs compute capability 7.0+ (or 6.1), float16 7.0+, bfloat16 8.0+.
How much does it cost to self-host Tabby?
The software is free to download. It needs a GPU server; we do not estimate that cost because GPU prices vary too much by card and provider.
Is Tabby free for commercial use?
Tabby is licensed under Apache-2.0 (ee directory under a separate license) (Open core). Internal business use is allowed under the license text. Everything outside the "ee/" directory is Apache-2.0. The ee/ directory has its own license. This is a summary, not legal advice.
What are common problems when self-hosting Tabby?
The CUDA image needs the NVIDIA Container Toolkit installed on the host. On SELinux systems you may need to add the :Z option to the volume mount.
Is Tabby still maintained?
Yes, it is actively developed. Last commit: Jun 30, 2026. Latest release: v0.32.0 (Jan 25, 2026). Checked Oct 22, 2026.
How do I install Tabby?
The official method is Docker (CUDA). The exact commands are in the "How to deploy" section above and in the official instructions: https://tabby.tabbyml.com/docs/quick-start/installation/docker/
Sources
- GitHub repository: github.com/TabbyML/tabby
- Official documentation, Deploy instructions, Gotcha 1, Gotcha 2: tabby.tabbyml.com/docs/quick-start/installation/docker/
- License text: github.com/TabbyML/tabby/blob/main/LICENSE
- Hardware requirements: tabby.tabbyml.com/docs/faq/
- 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.