Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
Latest release v3.1.0 — v3.1.0 — Corrected MTP labels, security notes, buyer snapshot and new reference pages · 2 Oct 2026
1 file for Codex and OpenCode: strix-halo-guide AGENTS.md — 2,053 tokens loaded in every session.
AGENTS.md A 2,053 tok These files are hogeheer499-commits/strix-halo-guide's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.