Flash-Next on Strix Halo: 91GB quant, 56 tok/s, 262k context

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.

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.

Optimised AMD toolchain by a llama.cpp contributor.

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.