Skip to content

Instantly share code, notes, and snippets.

@selfup
Last active May 11, 2026 01:49
Show Gist options
  • Select an option

  • Save selfup/1acf3cc41dbe2f28537dd3cc0c9f76b3 to your computer and use it in GitHub Desktop.

Select an option

Save selfup/1acf3cc41dbe2f28537dd3cc0c9f76b3 to your computer and use it in GitHub Desktop.
llama.cpp on Ubuntu x86 (3800x, 32GB RAM, 3060ti)
# wherever you have cloned the repo
cd ~/Documents/Repos/llama.cpp
# if you built relative to repo instead of user
# build in $HOME/.local
rm -rf build && cmake -B build \
-DGGML_CUDA=ON \
-DCMAKE_CUDA_ARCHITECTURES=86 \
-DBUILD_SHARED_LIBS=OFF \
-DCMAKE_INSTALL_PREFIX=$HOME/.local \
&& cmake --build build --config Release -j 8 \
&& cmake --install build \
&& which llama-server \
&& llama-server --version
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment