gufo
The Open Source Strix Halo AI engine. Qwen Flash Next Q4_K_XL: 1,773.82pp, 65.25tg single user, 184.74 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
- amd
- gfx1151
- llm
- ryzen-ai
- strix-halo
- Stars
- 766
- Forks
- 107
- + today
- —
- Created
- 2mo
Ranking data as of October 16, 2026 (UTC).
Overview
The Open Source Strix Halo AI engine. Qwen Flash Next Q4_K_XL: 1,773.82pp, 65.25tg single user, 184.74 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
The project is written in C++ and has 107 forks. It was created 2mo ago.
Installation
git clone https://github.com/gufo-org/gufo.git
cd gufo
# see README for setup