
ROCmForge
Decodes Qwen2.5-0.5B faster than llama.cpp on AMD GPUs.
Benchmarks
- On Radeon RX 7900 XT with Qwen2.5-0.5B (Q8_0), it decodes at 340.4 tok/s, against 239.2 tok/s for native llama.cpp reference (+42%). 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Something wrong or out of date?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.