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.
☆32Jun 9, 2026Updated 5 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☆22Oct 16, 2026Updated 3 weeks ago
- 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
- ☆56Sep 1, 2026Updated 2 months ago
- Linux retro-themed h/w monitor w/real-time telemetry & historical data. LAN-only by design.☆14Jun 17, 2026Updated 4 months ago
- llama.cpp setup on dedicated AMD Strix Halo machine☆14Jul 26, 2026Updated 3 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Unified terminal monitor for AMD Ryzen AI NPU (XDNA) + iGPU — live utilization for Strix Halo, where amd-smi comes up empty☆40Oct 18, 2026Updated 3 weeks ago
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆19Apr 26, 2026Updated 6 months ago
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆373Updated this week
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆28Aug 17, 2026Updated 2 months ago
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆85Updated this week
- RDMA fork version of Strix Halo inference engine. Qwen Flash Next Q4_K_XL: >2100pp …☆26Nov 4, 2026Updated last week
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆81Sep 9, 2026Updated 2 months ago
- 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…☆94Updated this week
- Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing …☆17Updated this week
- 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.
- Complete guide to running large language models locally on AMD Ryzen AI Max+ 395 (Strix Halo) with 128GB unified memory. Covers BIOS conf…☆122Dec 14, 2025Updated 10 months ago
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆225Oct 25, 2026Updated 2 weeks ago
- ☆12Aug 31, 2026Updated 2 months ago
- WMMA GEMM in ROCm for RDNA GPUs☆20Sep 1, 2026Updated 2 months ago
- Artifact-first agent framework — disciplined skill chain for AI-driven multi-step engineering tasks. MIT.☆21Sep 2, 2026Updated 2 months ago
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆18Oct 12, 2026Updated last month
- ☆62Aug 17, 2026Updated 2 months ago
- NEW ROCmfp4 format for llama.cpp☆159Jun 13, 2026Updated 4 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
- 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.
- ☆2,024Updated this week
- Run DeepSeek-V4-Flash-0731, GLM-5.3-Flash on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decod…☆16Oct 24, 2026Updated 2 weeks ago
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆88Nov 4, 2026Updated last week
- ☆94Oct 23, 2026Updated 2 weeks ago
- ☆549Nov 2, 2026Updated last week
- ☆23Oct 29, 2026Updated 2 weeks ago
- AI Business Operating System — run your business with AI agents. Local-first, multi-provider, governed.☆11Sep 4, 2026Updated 2 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…☆1,142Updated this week
- Tensor-parallel DeepSeek V4 Flash inference on dual AMD Strix Halo over OdinLink USB4/TB5 RDMA or Mellanox RoCE v2.☆23Sep 20, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Random AI notes for working with local models or playing around with random machine learning bits.☆63Jun 7, 2026Updated 5 months ago
- ReverseApp public release repo☆18Sep 9, 2026Updated 2 months ago
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆78Nov 4, 2026Updated last week
- ☆29Jun 10, 2026Updated 5 months ago
- LLM inference in C/C++☆43Nov 5, 2026Updated last week
- A deterministic inference engine for DeepSeek-V4.1-Flash 1017 and Qwen3.8-Flash-Next on a single AMD Strix Halo 128 GB☆21Updated this week
- ☆29Oct 11, 2026Updated last month
Are these results useful?