Copenhagen Local AI Meetup

​A meetup for developers, researchers, makers, and AI enthusiasts who want to run, build, and optimize AI systems on their own hardware.

​This community is focused on local and self-hosted AI: running large language models, multimodal models, agents, and supporting infrastructure without relying on external APIs. Whether you're experimenting on a laptop, running models on a workstation, building a GPU server, or operating a homelab, you'll find people working on similar challenges.

​Topics include:

• ​Running local LLMs with Ollama, llama.cpp, vLLM, SGLang, LM Studio, and Open WebUI

• ​Self-hosted AI infrastructure and inference servers

• ​Model optimization, quantization, fine-tuning, and distillation

• ​GPU performance, memory optimization, and hardware setups

• ​Agent frameworks and local-first AI applications

• ​MCP servers, tooling, and developer workflows

• ​Evaluation harnesses, benchmarks, testing, and observability

• ​Open-source AI ecosystems and emerging local AI tooling

• ​Privacy-preserving and offline AI deployments

​The format is simple: technical talks, lightning talks, demos, benchmarking sessions, and open discussion. Bring your projects, experiments, benchmarks, failures, lessons learned, and questions.

​This is not a startup-pitch meetup or a prompt-engineering meetup. We're here to discuss the practical realities of building and running AI systems locally: squeezing performance out of hardware, evaluating models rigorously, sharing infrastructure knowledge, and pushing open-source AI forward.

​Whether you're running a 7B model on a laptop, benchmarking agent frameworks, building custom evaluation harnesses, or serving frontier open models from your own GPUs, you're welcome.

​Come meet others building the future of local AI in Copenhagen.