open-weight model
A model whose trained weights, the learned numbers that define it, are published so anyone can download and run it under its licence.
In more detail
Open-weight models publish their trained weights, so they can run on your own hardware or a provider of your choice, which helps with data control, offline use and cost at scale. They are not necessarily open source: check the licence for limits on commercial use, and remember that you take on serving, updates and safety.
Related terms
- Ollama — An open-source tool that downloads open-weight models and serves them on your own machine through a local API.
- LM Studio — A desktop application for downloading and running open-weight models locally, with a built-in chat and a local server.
- closed model — A model whose weights stay with its provider, available only through the provider's API or apps.
Taught in
- Choosing A Model — AI Engineering: LLM Apps, RAG & Agents
- Structured Output — AI Engineering: LLM Apps, RAG & Agents
- When Context Fails — AI Engineering: LLM Apps, RAG & Agents
- What An Embedding Is — AI Engineering: LLM Apps, RAG & Agents
- Embedding Models — AI Engineering: LLM Apps, RAG & Agents
- Guardrails, Privacy And Governance — AI Engineering: LLM Apps, RAG & Agents
- Working With AI Coding Assistants — AI Engineering: LLM Apps, RAG & Agents
- Capstone: The Tasks Assistant — AI Engineering: LLM Apps, RAG & Agents