HolyGrAIL

All tasks / Tools

Docker Model Runner

Docker's built-in way to pull, run and serve models as OCI artifacts with llama.cpp or vLLM behind an OpenAI-compatible API.

  • Docker
  • Local only
  • Free, open source

Official site · Source code

Where it ranks

  • A
    Chat & assistants
    Runtimes & gateways · Local · via GLM-5.3-Flash
  • C
    Coding
    Runtimes & gateways · Local · via GLM-5.3-Flash

Tools without a benchmark of their own inherit the tier of the best model they offer.

Facts

Vendor
Docker
Approach
Runtimes & gateways
Where it runs
Runs only on your own hardware
Interface
Command line, Desktop app, API
Skill level
Intermediate: some setup or configuration
Price
Free, open source
Pricing notes
Included in Docker Desktop and Docker Engine; model runner code Apache-2.0.
Source code
Open source (Apache-2.0)
GitHub stars
659 (19 Oct 2026)
Last verified
19 Oct 2026

Price from github.com, 19 Oct 2026.

Models it gives you

Sources