One engine, every backend.
Veizik is one engine and one compiler. Each execution backend changes only the kernels and the device — the checkpoint you bring and the way you run it stay the same. Pick a backend for its execution path, features and install conditions; un-shipped backends are marked as what they are.
Choose a backend.
NVIDIA and Apple Silicon ship today; the edge CPU backend ships on single-board computers, with a Jetson preview and Android deployment pending.
NVIDIA
AvailableCUDA execution on NVIDIA GPUs, on Linux. Language, image and video models run from the checkpoint you already have — no CUDA toolkit and no Python at inference time.
- Backend
- CUDA
- Platform
- Linux on x86-64
Apple Silicon
AvailableMetal execution on Apple Silicon Macs. Language models run natively on the GPU from your own checkpoint, with no Python environment and no converted model copy.
- Backend
- Metal
- Platform
- macOS on Apple Silicon (arm64)
Edge · CPU
AvailableThe same engine on a single-board computer’s CPU — a Raspberry Pi 5 and a 512 MB Zero 2 W — with no desktop GPU. A native, compile-free kernel path on the Arm cores does the work a GPU would.
- Backend
- Arm CPU · NEON
- Platform
- Linux on Arm — Raspberry Pi 5 (Cortex-A76) and Raspberry Pi Zero 2 W (Cortex-A53).
Three catalogues, cross-linked.
The engines catalogue, the models catalogue and the hardware tables are bidirectional: a model names the backend it runs on, a device names the models verified on it, and each backend here links back to both.