AMD Unveils Day 0 Support for Qwen3.8 27B AI Model on Ryzen AI Max+ Processors and Radeon GPUs
AMD has launched Day 0 support for Qwen3.8 27B AI model on Ryzen AI Max+ processors and Radeon AI PRO R9700 GPUs.
The Qwen3.8 27B model, part of Alibaba Cloud's Qwen family, was released on August 14, 2026. It features enhanced long-context processing and hybrid Gated DeltaNet and Gated Attention layers.
Developers can run the model using open frameworks like llama.cpp, achieving impressive token throughput. Preliminary testing shows performance of up to 24.5 tokens per second on Ryzen AI Max+ 395 processors and 51.8 tokens per second on Radeon AI PRO R9700 GPUs.