Download Ollaya
One binary for Linux and macOS, or a Docker image.
Install with one command
curl -fsSL https://ollaya.dev/install.sh | shThe script detects your CPU and NVIDIA GPU, downloads the release from GitHub, checks its sha256 and, where systemd runs, sets up the ollaya service. With a GPU it also fetches the CUDA libraries (about 1 GB). It never installs drivers.
Run a model
ollaya run layaRequirements
- x86-64 or ARM64 with glibc 2.38 or newer: Ubuntu 24.04, Debian 13, Fedora 39, RHEL 10 or newer.
- Runs on the CPU. An NVIDIA GPU is optional: driver R580 or newer (CUDA 13), on x86-64.
- Windows: use WSL 2 with the Linux installer. A native Windows build is planned.
Install with one command
curl -fsSL https://ollaya.dev/install.sh | shThe script downloads the release from GitHub and checks its sha256. Start the server with ollaya serve, or let ollaya run start it for you.
Run a model
ollaya run layaRequirements
- A Mac with Apple silicon (arm64).
CPU
docker run -d --name ollaya -p 11435:11435 -v ollaya:/home/ollaya/.ollaya ghcr.io/ollaya-dev/ollayaNVIDIA GPU
docker run -d --name ollaya --gpus=all -p 11435:11435 -v ollaya:/home/ollaya/.ollaya ghcr.io/ollaya-dev/ollaya:cudaNeeds the NVIDIA Container Toolkit and a host driver with CUDA 13 support (R580 or newer).
Run a model
docker exec -it ollaya ollaya run layaThe CPU image is built for linux/amd64 and linux/arm64, the :cuda image for linux/amd64. Models are kept in the ollaya volume.
Prefer a tarball? Every release on GitHub Releases has the archives and a sha256sum.txt.