# Docker Model Runner Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/docker-model-runner
> Markdown URL: https://aitinkerers.org/technologies/docker-model-runner.md
> Technology record last updated: 2026-04-20T17:16:09Z
> Generated: 2026-09-22T14:47:07Z

Docker Model Runner standardizes local LLM deployment by wrapping high-performance inference engines like llama.cpp into portable, OCI-compliant containers.

Docker Model Runner eliminates the 'works on my machine' headache for AI engineering. It packages model weights and inference runtimes into a unified Docker image, allowing developers to spin up local APIs (compatible with OpenAI's schema) using a single command. By leveraging Docker Desktop's GPU passthrough for NVIDIA and Apple Silicon, it delivers near-native performance for models like Llama 3 or Mistral 7B without requiring complex local dependency management. This approach ensures that every member of a dev team runs the exact same model version and environment, accelerating the transition from local prototyping to production-ready microservices.

- Official technology site: https://github.com/docker/labs-ai-tools-for-devs
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Powering Local AI Agents With Real-Time Analytics](https://paris.aitinkerers.org/talks/rsvp_5xC5rIekf1Q)

We'll look at AI agents as a "new user persona" for real-time databases and explore how systems can adapt to their workloads. Finally, we'll demonstrate a fully local agentic workflow: a small open model running on-device with Docker Model Runner, connected through the ClickHouse MCP Server to ClickHouse Cloud — zero API keys,

- Event context: Offstage w/ Docker feat ClickHouse — 2026-07-07 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_5xC5rIekf1Q

### [Serverless Agentic Containers with Knative](https://paris.aitinkerers.org/talks/rsvp_5uatxgNgVi0)

When your agent is done with its task you want him to scale back to 0 replicas and you want to wake him up with an Event Driven approach, all of this configured with 5 lines of YAML : This is what SAIL (Serverless AI Layer) is, the new Open Source framework based on Kubernetes and Knative ! During the demo we will deploy 3 agents using a super streamlined Custom Resource , kickoff the first agent with a Kafka message and see the magic happen with all the agents starting collaborating together, sharing context and memory. We wil show how all of this can run locally on your machine, leveraging Kubernetes with Docker and inferring using Docker Model Runner.

- Event context: AI Tinkerers Paris: Docker Agentic Workflows (Devoxx Kickoff) — 2026-04-21 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_5uatxgNgVi0

## Related Technologies

- [ClickHouse](https://aitinkerers.org/technologies/clickhouse) ([Markdown](https://aitinkerers.org/technologies/clickhouse.md)) — 4 public demos
- [ClickHouse MCP Server](https://aitinkerers.org/technologies/clickhouse-mcp-server) ([Markdown](https://aitinkerers.org/technologies/clickhouse-mcp-server.md)) — 1 public demo
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Kafka](https://aitinkerers.org/technologies/kafka) ([Markdown](https://aitinkerers.org/technologies/kafka.md)) — 3 public demos
- [Knative](https://aitinkerers.org/technologies/knative) ([Markdown](https://aitinkerers.org/technologies/knative.md)) — 2 public demos
- [Knative/k8s](https://aitinkerers.org/technologies/knative-k8s) ([Markdown](https://aitinkerers.org/technologies/knative-k8s.md)) — 1 public demo
- [Kubernetes](https://aitinkerers.org/technologies/kubernetes) ([Markdown](https://aitinkerers.org/technologies/kubernetes.md)) — 35 public demos
- [LibreChat](https://aitinkerers.org/technologies/librechat) ([Markdown](https://aitinkerers.org/technologies/librechat.md)) — 2 public demos
- [Quarkus](https://aitinkerers.org/technologies/quarkus) ([Markdown](https://aitinkerers.org/technologies/quarkus.md)) — 1 public demo
- [Redis](https://aitinkerers.org/technologies/redis) ([Markdown](https://aitinkerers.org/technologies/redis.md)) — 23 public demos