GitHub · Python
rulith-dev/rulith-inference
Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.
- Stars
- 56
- Forks
- 6
- Stars gained in 24 hours
- +22
- Forks gained in 24 hours
- +3
Topics: amd, gfx1151, llama-cpp, local-llm, moe, qwen, rocm, strix-halo, windows
Latest data point: Nov 21, 2026 · 56 stars · 6 forks