pixmaate/gufo

The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

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 MoE). NPU prefill up to +28%, Flint 4.1k tok/s prefill, MTP / DFlash2 / auto speculative decoding up to 159 tok/s on structured text.

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.

Run Qwen3.8-Flash-Next on a single AMD Strix Halo using Halogen Flash Server

LLM inference in C/C++

A deterministic inference engine for DeepSeek-V4.1-Flash 1017 and Qwen3.8-Flash-Next on a single AMD Strix Halo 128 GB

The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)