#
beelink
Here are 4 public repositories matching this topic...
Strix Halo local LLM guide: 63-97 t/s direct MoE on Ryzen AI MAX+ 395 / 128GB unified memory. Setup, model choices, benchmarks, and raw evidence.
benchmark amd optimization vulkan inference rocm mini-pc unified-memory beelink llm llama-cpp local-llm ollama gguf rdna3 ai-pc strix-halo gfx1151 dgx-spark ryzen-ai-max
-
Updated
May 16, 2026 - Python
Make the front-panel power button work on Linux for IP3-Tech AMD Strix Halo mini-PCs (Corsair AI Workstation 300, Beelink, GMK, etc.)
linux mqtt home-assistant homeautomation gmk embedded-controller beelink strix-halo amd-ryzen-ai-max corsair-ai-workstation-300 acpi-wmi
-
Updated
May 8, 2026 - Python
Unlock fast, local LLM inference on AMD-powered mini PCs delivering 65-87 t/s for large models without cloud or subscription costs
amd optimization inference rocm mini-pc asus-rog linux-gaming unified-memory beelink cachyos llm llama-cpp local-llm ollama gguf rdna3 strix-halo gfx1151
-
Updated
May 16, 2026 - Shell
Improve this page
Add a description, image, and links to the beelink topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the beelink topic, visit your repo's landing page and select "manage topics."