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 mainline + ROCm 7.13 nightly + PyTorch 2.11 + bitsandbytes + flash-linear-attention all work together for multi-day LoRA training with out-of-process eval orchestration.
☆31Jun 9, 2026Updated 4 months ago
Alternatives and similar repositories for strix-halo-llm-finetune-guide
Users that are interested in strix-halo-llm-finetune-guide are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Oct 16, 2026Updated last 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 5 months ago
- Unified terminal monitor for AMD Ryzen AI NPU (XDNA) + iGPU — live utilization for Strix Halo, where amd-smi comes up empty☆38Oct 13, 2026Updated last week
- ☆56Sep 1, 2026Updated last month
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆362Oct 3, 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.
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆27Aug 17, 2026Updated 2 months ago
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆80Sep 9, 2026Updated last month
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆217Oct 9, 2026Updated last week
- Clean-room AGPL-3.0 reimplementation of the halogen 0.1.3 inference engine for Qwen3.8-27B on AMD Strix Halo (gfx1151) — same wire protoc…☆18Sep 10, 2026Updated last month
- Browser-based operator console for managing and monitoring Lemonade on Linux inference servers.☆20Aug 27, 2026Updated last month
- Lemonade Pi Agent CLI Plugin☆16Sep 12, 2026Updated last month
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆82Updated this week
- GPU + XDNA2 NPU inference for AMD Strix Halo (gfx1151): Qwen3.6-35B-A3B, Qwen3.8-27B and Qwen3.8 Flash-Next. NPU prefill +9% to +28%, MTP…☆74Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- LLM inference in C/C++☆42Updated this week
- qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included☆26Sep 24, 2026Updated 3 weeks ago
- Local inference with GMKTek evo-x2☆25Nov 3, 2025Updated 11 months ago
- ☆171Sep 2, 2026Updated last month
- NEW ROCmfp4 format for llama.cpp☆158Jun 13, 2026Updated 4 months ago
- ☆61Aug 17, 2026Updated 2 months ago
- ☆2,003Updated this week
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆73Aug 31, 2026Updated last month
- ☆15Oct 8, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆29Jun 10, 2026Updated 4 months ago
- Complete guide to running large language models locally on AMD Ryzen AI Max+ 395 (Strix Halo) with 128GB unified memory. Covers BIOS conf…☆117Dec 14, 2025Updated 10 months ago
- The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B…☆849Updated this week
- ☆11Oct 4, 2026Updated 2 weeks ago
- ☆537Updated this week
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆72Updated this week
- Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini P…☆198Updated this week
- Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a m…☆40Updated this week
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 4 months 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.
- ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch☆21Feb 4, 2026Updated 8 months ago
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆86Oct 14, 2026Updated last week
- ☆29Jul 30, 2026Updated 2 months ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆85Sep 16, 2026Updated last month
- Qwen3.8 Flash Next AWQ INT4 4x3090 v1: 262K, Vision, FP8 QSA KV and CUDA Graphs on 4x RTX 3090☆16Aug 30, 2026Updated last month
- Hermes Agent benchmark v0.1 — evaluate local models on the actual tool-calling patterns Hermes users hit. Reproducible, trace-capturing, …☆16Jun 24, 2026Updated 3 months ago
- LLM inference in C/C++☆240Updated this week