aic0d3r / qwen38-strix-halo-harness
22Local AI coding agent for AMD Strix Halo (Ryzen AI Max+ 395): Qwen3.8 125B on the Radeon 8060S iGPU via llama.cpp, small models on the NPU, crash recovery, logged benchmarks. No API key needed, cloud optional.
📦 Otheruniversal