AMD Strix Halo local LLM guide: setup for Ryzen AI MAX+ 395 / Radeon 8060S, Ollama, llama.cpp Vulkan/RADV, ROCm, raw evidence, direct 100 t/s 30B Qwen, 140 t/s CHADROCK MTP, 120B GGUF.
-
Updated
Jun 21, 2026 - Python
AMD Strix Halo local LLM guide: setup for Ryzen AI MAX+ 395 / Radeon 8060S, Ollama, llama.cpp Vulkan/RADV, ROCm, raw evidence, direct 100 t/s 30B Qwen, 140 t/s CHADROCK MTP, 120B GGUF.
FrameworkDotnet is a .NET library for talking to Framework laptop and desktop embedded controller APIs through the native framework-system Rust FFI layer.
An exercise in futility and wasting electricity: this repo contains an Unsloth build environment for training a finetuned Gemma 4 LLM for home-assistant tool calls. Built with AMD ROCm on a Framework Desktop using Nix package manager + UV for a reproduceable build environment.
Known-good local LLM inference on the Framework Desktop (Ryzen AI Max+ 395 / Strix Halo)
Manual per-fan control + live temps/RPM for the Framework Desktop (cros_ec) on Linux — GTK4 app with a minimal root daemon.
Standalone native FFI facade for framework-system, intended for .NET interop via csbindgen.
A collection of NixOS system configurations for different machines.
Add a description, image, and links to the framework-desktop topic page so that developers can more easily learn about it.
To associate your repository with the framework-desktop topic, visit your repo's landing page and select "manage topics."