LattePanda Team today launched LattePanda Mu Ultra, a micro x86 compute module purpose-built for on-device AI. Powered by Intel Core Ultra 5 226V and Ultra 7 256V processors, it delivers up to 115 TOPS of AI performance in a compact 69.6 mm × 60 mm form factor. Built to address hardware, compute, and software challenges of running AI locally, LattePanda Mu Ultra brings powerful AI computing to engineering teams, system integrators, and OEMs across robotics, industrial automation, portable instruments, vision AI, and intelligent edge applications.

LattePanda Mu Ultra combines the CPU, GPU, and NPU of Intel Core Ultra processors to deliver up to 115 TOPS (INT8), including 47 TOPS from the dedicated NPU. In testing, it achieved text generation speeds of 18 tokens/s with Qwen3.5-9B and 55 tokens/s with Qwen3.5-2B using INT4 quantization with OpenVINO Gen AI. The module features 16 GB of LPDDR5X-8533 memory with up to 11.6 GB available for graphics, and idle power consumption as low as 2.5 W.

LattePanda Mu Ultra supports Windows and Linux, maintaining compatibility with the established x86 software ecosystem and popular AI tools including Intel OpenVINO, llama.cpp, and Ollama. It retains the standardized form factor and connector of the LattePanda Mu family for modular upgrades.