From b4f77d68825f411afae08c79021a5a057fd0c51b Mon Sep 17 00:00:00 2001 From: hogeheer499-commits Date: Sun, 9 Aug 2026 03:38:13 +0200 Subject: [PATCH] docs: add AMD Strix Halo local LLM guide --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index d33fba1..86b9aea 100644 --- a/README.md +++ b/README.md @@ -468,6 +468,7 @@ Most self-hosted software can be installed using [Docker](https://en.wikipedia.o **Large Language Models (LLMs)** is a language model that uses artificial neural networks to generate text (AI chatbots/search engines). Some notable ones are GPT-3, GPT-4, BLOOM, and LLaMA. * [A comprehensive guide to running Llama 2 locally](https://replicate.com/blog/run-llama-locally) + * [AMD Strix Halo Local LLM Guide](https://github.com/hogeheer499-commits/strix-halo-guide) — Copyable Ryzen AI MAX+ 395 setup with Vulkan/RADV and ROCm routes, reproducible benchmarks, raw logs, failed paths, and cross-system evidence. * [Leaderboard by lmsys.org](https://chat.lmsys.org/?leaderboard) * [LLM-Leaderboard](https://github.com/LudwigStumpp/llm-leaderboard) * [Open LLM Leaderboard by Hugging Face](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)