Specifications SpecificationParameterProcessor SoCAX630C Dual Cortex A53 1 2 GHzMAX 12 8 TOPS INT4 3 2 TOPS INT8Memory4GB LPDDR4 1GB system memory 3GB dedicated to hardware acceleration Storage32GB eMMC5 1CommunicationSerial communication default baud rate 115200 8N1 adjustable MicrophoneMSM421AAudio DriverAW8737Speaker8Ω 1W size 2014 cavity speakerBuilt in FunctionsKWS wake word ASR speech recognition LLM large language model TTS text to speech RGB LED3x RGB LED 2020 driven by LP5562 status indicator Power ConsumptionNo load 5V 0 5W Full load 5V 1 5WButtonUsed to enter firmware download modeUpgrade InterfaceSD card Type C portConversion ChipCH340NEthernet InterfaceRJ45 interface with onboard network transformer 11FB 05NL SOP 16 Serial InterfacesFPC 8P interface Type C interface RJ45 interfaceDIY ExpansionHT3 96 9P solder padOperating Temp 0 40°CProduct SizeModule LLM 54 0 x 54 0 x 13 0mmModule13 2 LLM Mate 54 x 54 x 19 7mmPackage SizeModule LLM 192 0 x 95 0 x 17 0mmModule13 2 LLM Mate 192 0 x 95 0 x 21 0mmProduct WeightModule LLM Module13 2 LLM Mate 36 7g Introduction 1 Module LLM Kit is a smart modular kit focused on offline AI inference and data communication interface applications It integrates the Module LLM and Module13 2 LLM Mate modules to meet the offline AI inference and data interaction requirements across various scenarios 2 Module LLM is an integrated offline large language model LLM inference module designed specifically
