
QVAC Fabric
Offloads work to Core ML on Apple Silicon and to the XDNA NPU on AMD, in a llama.cpp fork. It is a fork of ggml-org/llama.cpp.
Benchmarks
- On M3 Ultra with Qwen3.8-27B (Q4_0), it reads prompts at 470.5 tok/s, against 341.7 tok/s for Core ML off (+38%). Source
- On Ryzen AI MAX+ 395 with Qwen3.5-2B (Q4_K_M), it decodes at 61.9 tok/s, against 20.1 tok/s for XDNA NPU off (3.1×). Source
Listing
Listed: Passed all seven checks.
Security review
Not reviewed yet.
Install
To install it, follow the project's own instructions on GitHub. The engine runs with your user's permissions. macOS doesn't sandbox it, so install only engines you trust.
Something wrong or out of date? Write to help@kalsa.io, or ask us to remove this page.