Ollama

Community

Run large language models locally — pull and serve open models like Llama, Qwen, and Gemma through a simple REST API.

Runs	ollama/ollama:0.40.5
Stack	go
Provisioned for it	Nothing, it's self-contained
Verified	Not yet

Why deploy on Railyard

Railyard runs it standalone on a server you already pay for — no addons to provision, with zero-downtime deploys and scaling still included.

Deploying Ollama is one piece of a bigger stack you can keep building — add a database, a worker, a cache, or another app, all on the same servers you already pay for.

Good for

Self-hosted LLM inference for Open WebUI, Langflow, or a custom app
Running open models like Llama and Qwen without sending data to a third-party API
A local OpenAI-compatible endpoint for development

Good to know

No GPU is attached automatically — CPU-only inference works but is slow for larger models
Nothing is bundled by default — pull a model after deploy, e.g. `ollama pull llama3.2`

Project docs ↗