Strix Halo + ROCm 7.1 + Ubuntu

Install ROCm 7.1 on the AMD Strix Halo (GMKtec EVO X2, AI MAX+ 395) running Ubuntu 24.04. This step-by-step guide covers kernel 6.14 upgrade, AMD GPU driver installation, ROCm setup, and shared memory (TTM) configuration with amdttm — everything you need to start running ComfyUI, Ollama, and Llama CPP locally. 0:00 - Intro 0:17 - What ROCm 7.1 Enables 0:53 - Fresh Ubuntu Server Setup 1:24 - Supported vs Unsupported GPUs 2:08 - SSH In & Prerequisites 2:54 - Upgrade Kernel to 6.14 3:35 - Verify Kernel & Full Update 3:53 - Install AMD GPU Drivers & ROCm 5:08 - Verify ROCm Installation 5:41 - Set Up Shared Memory with amdttm 7:09 - Apply TTM Settings & Reboot 8:15 - Verify Setup & Next Steps 8:44 - Wrap Up Related Products (affiliate links help support my content at no extra cost to you, thanks!): - GMKtec EVO-X2 (AI MAX+ 395): https://www.amazon.com/dp/B0F53MLYQ6?tag=hakehardware-20 - GMKtec M7 Mini PC: https://www.amazon.com/dp/B0DQKRXKS5?tag=hakehardware-20 - Samsung 990 EVO Plus SSD: https://www.amazon.com/dp/B0DHLBDSP7?tag=hakehardware-20 - Crucial 96GB DDR5 5600MHz RAM: https://www.amazon.com/dp/B0C79K5VGZ?tag=hakehardware-20 - Tripp Lite 1500VA UPS: https://www.amazon.com/dp/B000DZRY9C?tag=hakehardware-20 Related Videos: - ComfyUI + ROCm 7.1 + PyTorch 2.8 + Strix Halo: https://youtu.be/8a_oANfzQ-8 - ComfyUI on AMD 780M with Zluda: https://youtu.be/LVjOoTJ4NiQ - Local AI with a Mini PC is Totally Usable: https://youtu.be/ve4pR7OrEsQ - Ollama with AMD support on Windows: https://youtu.be/AgLL-mmlG9Y - Testing Qwen3-coder-30b with a Mini-PC: https://youtu.be/y7IHTVa8lL8 Guide: https://localhake.com/content/strix-halo-rocm-71-ubuntu-2404 #StrixHalo #ROCm #AMD