A two-day, non-expert guide to running local LLMs on an AMD Strix Halo (Ryzen AI Max+ 395) box — full ~120GB memory pool, ROCm backend, NPU in parallel via FastFlowLM, one OpenAI-compatible endpoint.
-
Updated
Jul 25, 2026
#
fastflowlm
Here are 8 public repositories matching this topic...
Flm Companion is a lightweight Windows desktop app that simplifies managing your local FastFlowLM CLI server. It offers an intuitive interface to start, stop, and monitor the LLM, manage models, and check updates without command line use.
-
Updated
Oct 21, 2026 - TypeScript
Fedora COPR packaging for FastFlowLM - Run LLMs on AMD Ryzen AI NPUs
amd fedora rpm epel copr xrt npu rpm-packaging almalinux llm xdna local-llm llm-inference ryzen-ai strix-halo fastflowlm amd-npu xdna-driver
-
Updated
Oct 29, 2026 - Makefile
A converter for transferring gguf Q8_0, Q4_0, Q4_1, MXFP4, or raw tensors to FLM Q4NX
-
Updated
Aug 17, 2026 - Python
Unlocking the power of the Halo NPU: NPU + iGPU live verification, compression, and routing research on AMD Strix Halo
-
Updated
Sep 11, 2026 - Python
Solving high school math questions with local LLMs
-
Updated
Apr 12, 2026 - Python
Make the Copilot/AI key on your Linux laptop do something: chat, translate and explain text or a screenshot in your language. Runs on the AMD Ryzen AI NPU, offline. KDE Plasma.
-
Updated
Nov 1, 2026 - Python
On-device semantic search & RAG over any folder — running on your NPU (AMD Ryzen AI / Intel). Private, local-first, low-power. The memory layer of the Antumbra platform.
rust cli privacy embeddings semantic-search rag openvino npu vector-search llm local-ai ai-pc ryzen-ai fastflowlm
-
Updated
Aug 11, 2026 - Rust
Add this topic to your repo
To associate your repository with the fastflowlm topic, visit your repo's landing page and select "manage topics."