# Gygeek/Framework-strix-halo-llm-setup

<https://repo.masters-masters.com/en/repos/Gygeek/Framework-strix-halo-llm-setup>

[Home](https://repo.masters-masters.com/en) › [Gygeek](https://repo.masters-masters.com/en/owners/Gygeek) › [Framework-strix-halo-llm-setup](https://repo.masters-masters.com/en/repos/Gygeek/Framework-strix-halo-llm-setup)

Gygeek/Framework-strix-halo-llm-setup has 121 stars on GitHub. Its RepoMasters card: Prototype tier. Complete guide to running large language models locally…

| Field | Value |
| --- | --- |
| Owner | [Gygeek](https://repo.masters-masters.com/en/owners/Gygeek) |
| Stars | 121 |
| Forks | 9 |
| Language | No language |
| License | None |
| Created | 2025 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [Gygeek/Framework-strix-halo-llm-setup](https://github.com/Gygeek/Framework-strix-halo-llm-setup) |

## Repository

Complete guide to running large language models locally on AMD Ryzen AI Max+ 395 (Strix Halo) with 128GB unified memory. Covers BIOS config, kernel setup, ROCm installation, and llama.cpp deployment. Run 70B+ parameter models on a single APU.

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.