AIPython★ 373⑂ 28 forksMIT
hogeheer499-commits/strix-halo-guide
STRIX HALO LLM Setup
Guide for LLM on Ryzen AI MAX+ 395 and Radeon 8060S via Ollama, llama.cpp and ROCm. Achieving 100 tokens/s 30B Qwen and 140 tokens/s CHADROCK MTP.
// KEY FEATURES
- Ollama + llama.cpp with Vulkan/RADV acceleration
- ROCm support for Radeon 8060S and Ryzen AI MAX+
- 100 tokens/s 30B Qwen, 140 tokens/s CHADROCK MTP
#amd#beelink#benchmark#framework#framework-desktop#gfx1151#gguf#llama-cpp#llm#local-ai#local-llm#mini-pc
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram