M5Stack LLM Module Kit (AX630C)

The M5Stack LLM (Large Language Model) Kit is an offline AI inference and data communication interface add-on, delivering a smooth and natural AI experience without relying on the cloud, ensuring privacy, security, and stability. The LLM module provides a variety of interface functions to facilitate system integration and expansion. It achieves stacked power supply from a Core unit via the M5BUS interface; its built-in CH340N USB conversion chip offers USB-to-serial debugging functionality, while the USB-C interface is used for USB log output. An RJ45 interface works with the onboard network transformer to extend to a 100 Mbps Ethernet port and core serial port (supporting SBC applications); the FPC-8P interface connects directly to the LLM module, ensuring stable serial communication. An HT3.96x9P solder pad is also reserved for DIY expansion. The module integrates the StackFlow framework along with the Arduino/UiFlow libraries, allowing edge intelligence to be implemented with just a few lines of code. Powered by the advanced AiXin AX630C SoC processor and featuring a high-efficiency NPU delivering 3.2 TOPS with native support for Transformer models, it effortlessly handles complex AI tasks. Equipped with 4GB LPDDR4 memory (1GB for user applications and 3GB dedicated to hardware acceleration) and 32GB eMMC storage, it supports parallel multi-model loading and chained inference. With an operating power consumption of ~1.5W, it is far more energy efficient than similar products. It's compatible with multiple models and comes pre-installed with the Qwen2.5-0.5B large language model, featuring built-in functions including KWS (wake word), ASR (speech recognition), LLM (large language model), and TTS (text-to-speech). It also supports apt-based rapid updates of software and model packages. By installing the openai-api plugin, it becomes compatible with the OpenAI standard API, supporting chat, conversation completion, speech-to-text, and text-to-speech among various application modes. The official apt repository offers abundant large model resources, including deepseek-r1-distill-qwen-1.5b, InternVL25-1B-MPO, Llama-3.2-1B, Qwen2.5-0.5B, and Qwen2.5-1.5B, as well as text-to-speech models (whisper-tiny, whisper-base, melotts) and visual models (such as yolo11 and other SOTA models). The repository is continuously updated to support the most cutting-edge model applications, meeting the demands of complex AI tasks. The kit is plug-and-play, and when paired with an M5 host, it provides an instant AI interactive experience. Note: The models supported by the Module LLM are in a special format unique to AXERA and require special processing to be used normally. Therefore, existing models on the market cannot be used directly.

Features

* Offline inference, 3.2 TOPS at INT8 precision

* Integrated KWS (wake word), ASR (speech recognition), LLM (large language model), TTS (text-to-speech)

* Parallel multi-model processing

* Onboard 32GB eMMC storage and 4GB LPDDR4 memory

* Onboard microphone and speaker

* Serial communication

* SD card firmware upgrade

* Supports ADB debugging

* RGB status LED

* Built-in Ubuntu system

* Supports OTG functionality

* Development Platform

* UiFlow2

* Arduino IDE

Specifications

Processor SoC AX630C@Dual Cortex A53 1.2 GHz

MAX.12.8 TOPS @INT4, 3.2 TOPS @INT8

Memory 4GB LPDDR4 (1GB system memory + 3GB dedicated to hardware acceleration)

Storage 32GB eMMC5.1

Communication Serial communication, default baud rate 115200@8N1 (adjustable)

Microphone MSM421A

Audio Driver AW8737

Speaker 8Ω@1W, size: 2014 cavity speaker

Built-in Functions KWS (wake word) ASR (speech recognition) LLM (large language model) TTS (text-to-speech)

RGB LED 3x RGB LED @ 2020, driven by LP5562 (status indicator)

Power Consumption No load: 5V @ 0.5W, Full load: 5V@1.5W

Button Used to enter firmware download mode

Upgrade Interface SD card/Type-C port

Conversion Chip CH340N

Ethernet Interface RJ45 interface with onboard network transformer (11FB-05NL SOP-16)

Serial Interfaces FPC-8P interface, Type-C interface, RJ45 interface

DIY Expansion HT3.96*9P solder pad

Operating Temperature 0-40°C

Resources

* Product Wiki

Tutorials and guides

* Arduino Quick Start

* Arduino Library

* Arduino Library API

* UiFlow2 Quick Start

* UiFlow2 API

* OpenAI API tutorial

* StackFlow

* ADB / SSH / UART Connect

* Software Update

* Image Update

Documentation

* Module LLM Schematic Download

* Module 13.2 LLM Mate Schematic Download

* Module LLM Dimensions

* Module 13.2 LLM Mate Dimensions

* AX630C datasheet

Development Resources

* AX630C Databrief

* Module LLM JSON API Documentation

* Module LLM AX630C API Docs

* Module LLM AX620E MSP/Sample

* Module LLM Linux Kernel 4.19.125-head

* AXERA LLM Example

* AXERA CV Example

* Module LLM Large Model Compilation Guide

Package Contents

* 1 x LLM Module

* 1 x LLM Mate Module

* 2 x 8-Pin FPC Cable