News for hackers. Stuff that matters.
Re:Stop Using Ollama by erusev on Thursday April 16, 2026 @08:55AM (#47792317)
This is partly why we're building LlamaBarn. It's a lightweight macOS menu bar app that runs llama-server under the hood, with models stored as standard GGUFs in your Hugging Face cache — the same location llama-server uses by default. No separate model store, no lock-in.

https://github.com/ggml-org/LlamaBarn

There are no comments on this comment yet.