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.
☆124Dec 14, 2025Updated 11 months ago
Alternatives and similar repositories for Framework-strix-halo-llm-setup
Users that are interested in Framework-strix-halo-llm-setup are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆28Jul 29, 2026Updated 3 months ago
- ☆2,033Updated this week
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆373Nov 9, 2026Updated last week
- Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux ma…☆32Jun 9, 2026Updated 5 months ago
- LLM Fine Tuning Toolbox images for Ryzen AI 395+ Strix Halo☆67Sep 12, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Tools and documentation related to the AMD Strix-Halo AGU family (Ryzen AI Max 395) of systems. Tested on GMKtec EVO-2☆12Dec 14, 2025Updated 11 months ago
- ☆20Sep 4, 2025Updated last year
- ☆186Sep 2, 2026Updated 2 months ago
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆74Aug 31, 2026Updated 2 months ago
- ☆56Sep 1, 2026Updated 2 months ago
- Proxmox GPU Passthrough Guide for AMD Ryzen AI Max+ 395 (Strix Halo / 8060S)☆54Sep 12, 2025Updated last year
- llama.cpp setup on dedicated AMD Strix Halo machine☆14Jul 26, 2026Updated 3 months ago
- ☆111Aug 28, 2026Updated 2 months ago
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆88Nov 4, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- GPU + XDNA2 NPU inference for AMD Strix Halo (gfx1151): Qwen3.6-35B-A3B, Qwen3.8-27B, Qwen3.8 Flash-Next, Flint and GLM-5.3 Flash (321B M…☆96Nov 12, 2026Updated last week
- Vitronia — Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151): 30 to 58 tok/s on Vulkan. Draft-head speculation, measurements, pitfalls, repr…☆14Sep 21, 2026Updated last month
- ☆15Dec 13, 2022Updated 3 years ago
- various scripts to be used in conjunction with GeekTool or Ubersicht☆19Mar 30, 2025Updated last year
- Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.☆270Sep 7, 2026Updated 2 months ago
- Fresh builds of llama.cpp with AMD ROCm™ acceleration☆827Updated this week
- Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthrop…☆1,377Updated this week
- A prompt generator for my fork of the extended_openai_conversation HomeAssistant custom integration.☆13Apr 14, 2025Updated last year
- vaultwarden_zhcn中文汉化版本☆11May 12, 2026Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 7…☆40Nov 2, 2026Updated 2 weeks ago
- Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https…☆6,243Updated this week
- ☆23Jun 26, 2024Updated 2 years ago
- Beginner-friendly awesome list and guides for Hermes Agent by Nous Research. Install, skills, memory, MCP, cron, workflows, security, and…☆45Nov 4, 2026Updated 2 weeks ago
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 5 months ago
- ☆13May 7, 2026Updated 6 months ago
- ☆177Apr 7, 2026Updated 7 months ago
- ☆11Nov 7, 2021Updated 5 years ago
- DevTools for multi-agent AI — trace, visualize and debug agent workflows in real time☆17Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Qwen 3.8 Next Flash toolbox utilizing pwilkin's strix-halo llama.cpp fork☆13Sep 16, 2026Updated 2 months ago
- LLM inference in C/C++☆42Updated this week
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆53May 10, 2026Updated 6 months ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆21Oct 16, 2026Updated last month
- ☆16Sep 29, 2026Updated last month
- Hybrid SCCM-to-Intune zero-touch device registration framework reducing provisioning time from 6.5 hours to 30 minutes☆17May 28, 2026Updated 5 months ago
- Knows your world. Answers to you. — the open-source personal AI agent you own.☆18Updated this week
Are these results useful?