Is it safe to delete llama.cpp model cache?
Model files llama.cpp downloaded from a web address or Docker Hub, and Hugging Face models saved by older versions.
Usually safe
It can be recreated, but it takes a download, a reinstall or the tool's own command.
~/
What it is
When you start llama.cpp's tools with a model's web address or a Docker Hub name, they download the GGUF file into this folder and reuse it next time. Earlier versions saved Hugging Face downloads here too; current versions use the shared Hugging Face cache instead. Files stay until they're removed.
If it's removed
The next command that uses a removed model downloads it again before it starts.
How it's removed
Moved to the Trash, where you can restore it.
The free analyzer finds it and explains it. Removing it is Pro, after a review sheet that lists every move and command. It's never checked for you: it waits for your choice.
Sources
- github.com/ggml-org/llama.cpp/blob/master/common/common.cpp
- github.com/ggml-org/llama.cpp/blob/master/common/hf-cache.cpp
- github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md
Last checked on 26 Sep 2026. Every entry is written and checked by hand; the app and the command-line tool use the same words.