Chat with my docs on a laptop, no GPU (easiest)
AnythingLLM Desktop + built-in embedder + Ollama qwen3:4b or qwen3:8b (Q4). 16GB RAM. Turn on the reranker. Under 1 hour.
Draft recipe This setup is assembled from each project's documentation and community reports. It has not yet been tested end to end by RAGShelf.
Tools in this recipe
- AnythingLLM Active
- Ollama Active
Last updated 2026-10-24
The RAGShelf weekly
New local RAG tools, releases, and tested setups. One email a week, no spam.