Skip to main content
Koharu downloads the native libraries and model files needed by the features you use. You do not need a full CUDA or ROCm SDK installation to run a release.

​
Device selection

Startup chooses a shared ML device from the available backends: Metal on Apple silicon, then CUDA, ROCm/HIP, Vulkan, or CPU where supported. The operating system, driver, model backend, and published runtime packages must all support the selected path.
CUDA 13.0 support is available on Windows and Linux. Use a Turing-class or newer GPU and an R580-series or newer driver. See NVIDIA’s driver and architecture matrix and driver downloads.
The editor canvas uses WebGPU in the embedded CEF webview. It still needs a working WebGPU adapter and graphics driver when ML inference runs on CPU.

​
Downloads and caches

Packages live under the operating system cache directory in koharu/packages. Projects live under Documents/Koharu; settings live in ~/.koharu/config.toml. See data locations. Downloads are staged before being published to the cache. Retry an interrupted download on the next launch or model use.

​
Memory and model residency

The resource monitor reports host memory, compute activity, and model residency. Models load lazily and may remain resident for reuse. Koharu can evict idle models when a later stage needs memory. Start with a moderate local quantization. Smaller files usually need less memory, with a possible quality trade-off. A model that fits on disk can still exceed device memory. If startup fails, check network access to the package repositories, update the driver, and retry once. Capture the full error if it repeats and follow troubleshooting.