Acer has entered the Strix Halo mini PC race with the Veriton RA110, a 160 x 160 x 47 mm (6.3 x 6.3 x 1.9 inch) chassis built around AMD's Ryzen AI Max+ 395. The 16-core, 32-thread Strix Halo processor pairs with the 40-core Radeon 8060S integrated GPU and up to 128GB of LPDDR5x-8533 memory running at 256GB/s, putting discrete-class graphics and AI workloads into a footprint smaller than many NUC-style boxes.
Acer is pitching the RA110 as a mini workstation, citing up to 126 TOPS of AI performance and enough unified memory to load 200-billion-parameter LLMs locally. The same silicon that makes it appealing for on-device inference also makes it a credible compact gaming PC, since the Radeon 8060S is the strongest integrated GPU AMD currently ships. It's a touch larger than AMD's own Ryzen AI Halo mini PC, but still tiny for the hardware inside.
Storage is handled by two M.2 2280 slots, and wireless connectivity covers WiFi 7 and Bluetooth 5.4. The port array includes one 2.5 Gigabit Ethernet jack, two USB4 Type-C ports, two USB 3.2 Gen 2 Type-A ports, HDMI 2.1, a 3.5mm audio jack, an SD card reader, and a DC power input. There's no mention of an OCuLink or external GPU pathway, which tracks with how most Strix Halo systems have shipped so far.
Acer plans to sell the Veriton RA110 in select markets including North America in the second half of 2026, with pricing to be announced closer to launch. Linux users eyeing the box should find a familiar story with Strix Halo, which has been working its way into mainline kernel and Mesa support alongside the rest of AMD's 2026 lineup. Phoronix benchmarks on other Strix Halo hardware found that Ubuntu 26.04 with the Linux 7.0 kernel and Mesa 26.0 delivered meaningful gains for the Radeon 8060S across both Vulkan and OpenGL workloads compared to earlier software stacks. For local LLM inference, the open-source community has built out substantial tooling around this platform, with llama.cpp and the Mesa RADV Vulkan backend offering the most practical path to GPU-accelerated inference, as covered in community setup guides and a dedicated llama.cpp build targeting Strix Halo specifically.
