
paperniuk/splash
Runs Splash on M1 and M2 Macs, where the upstream needs an M3 or newer. It is a fork of incoai/splash.
What it does better
Runs Splash 1.6.1 on M1 and M2 Macs, where the upstream needs an M3 or newer; on an M1 Max with 64 GB it decodes Qwen3.8-27B 4-bit at 57 tok/s with one request and 63 tok/s with two at once
Trade-off: on an M3 or newer the author says to use the official Splash; nothing in this fork is faster there.
Benchmarks
The author hasn't published benchmarks yet.
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Something wrong or out of date?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.