RTX 3060 MXM GPU Carrier Board Kit for LattePanda Mu (Local AI & 6x 4K Output)

The LattePanda Mu RTX 3060 MXM Carrier Board Kit delivers a highly integrated, ready-to-deploy system.The LattePanda Mu MXM GPU Carrier board is a compact board that bridges the LattePanda Mu compute module with a discrete MXM graphics card. It delivers scalable compute within a tiny form factor. Engineered for space-constrained scenarios, it is purpose-built for local AI inference (LLMs, VLMs, GenAI) via GPUs like the RTX 3060, and high-density visual applications supporting up to six independent 4K displays.

Note: Compute Module Required, the LattePanda Mu Compute Module is NOT included. Please purchase it separately to complete the system.

Small Form, Massive Compute

The LattePanda Mu MXM GPU Carrier is a compact-form-factor carrier board designed to integrate a discrete MXM graphics card within a minimal footprint. With robust 3D rendering and AI inference capabilities, it excels whether you're running heavy game-engine-based (Unity / Unreal) interactive art installations or directly driving a multi-screen 4K display matrix. Crucially, its highly integrated design allows you to effortlessly embed it into tight spaces or mount it discreetly behind displays, perfectly balancing the computing demands for high performance with a tiny physical size. With an overall size of 159 × 107.5 × 88.5 mm, the kit is compact enough for embedded display systems, kiosk controllers, interactive installations, and edge AI prototypes where a standard desktop GPU system is too large.

6-Channel 4K Video Output

Unleash massive visual real estate. With 6 video outputs (LattePanda Mu 2-ch + MXM GPU 4-ch), you can easily build a video wall. Each channel supports 4K@60Hz hardware decoding, delivering smooth and stutter-free visuals for high-end digital signage and control rooms.

Two Powerful GPU Kit Options

Two distinct versions of the MXM GPU Carrier Board Kit are available to meet diverse computing requirements. This page details the NVIDIA GeForce RTX 3060 Kit, engineered for high-performance workloads.

Targeting High-Performance Edge Compute (RTX 3060 / 12GB VRAM): When paired with the included NVIDIA RTX 3060 MXM GPU, this system operates as a powerhouse for heavy local AI and intensive rendering tasks. Complex computer vision, visual-language models, and image generation are handled with ease. Furthermore, the setup is capable of running INT4-quantized LLMs up to around 9B parameters (depending on the framework and runtime configuration). It stands as the ideal choice for scenarios requiring massive VRAM and uncompromised edge compute, such as demanding interactive installations and advanced AI prototypes.

For a highly cost-effective, ultra-low-power edge AI solution, please refer to the A380 MXM GPU Carrier Board Kit.

Modular CPU Configuration

Fully compatible with all the LattePanda Mu compute modules. Drop in either the Intel N100 or Core i3-N305 processor based on your deployment requirements. This decoupled architecture allows you to scale CPU compute independently from the MXM GPU selection.

Important Note: