gfx1151-engine: custom inference framework for the AI MAX 395

LaikaSep 1964 stars

An inference engine written for Ryzen AI MAX 395 on Linux and Windows that deploys only Qwen-family MoE models. The author is an automation engineer, not a full-time programmer, who built it to get more out of his mini PC.

Open on GitHub

Preview of gfx1151-engine: custom inference framework for the AI MAX 395

Launch: Qwen3.8-Flash-Next
Use case: Amd local
Format: Repo
Source: github.com

Laika

I work in the automation industry, not a professional programmer. I make small tools in my spare time.

See all

peonist-ai

@peonist-ai · Aug 26

Container-based server tuned for the gfx1151 Strix Halo APU, aimed at squeezing maximum tokens per second from the 125B model on a mini-PC.

pwilkin

@pwilkin · Sep 5

Optimised AMD toolchain by a llama.cpp contributor.

Niko1221

@Niko1221 · Sep 24

Open-source inference engine with an OpenAI/Anthropic-style local API that fits the 125B MoE onto a 12GB consumer GPU plus system RAM. The project behind the model's local-running surge.

MiaAI-Lab

@MiaAI-Lab · Sep 4

Step-by-step recipe to squeeze the 125B model onto one DGX Spark instead of two, with config and measured throughput.

Open on GitHub

gfx1151-engine: custom inference framework for the AI MAX 395

More built with Qwen3.8-Flash-Next