Industrial Edge AI
2026-08-2710 min read

Zhongda Tech K3 Industrial Edge AI Module: 60 TOPS RISC-V on Mini COM-E

On August 27, 2026, Zhongda Tech announced an upcoming industrial edge AI compute module built on the SpacemiT K3 RISC-V SoC. In a standard Mini COM-E form factor (84×55 mm), it delivers 130 KDMIPS of general-purpose compute and 60 TOPS of AI inference — enough to run a 30-billion-parameter LLM locally. With a 100% domestic supply chain, -40°C to 70°C industrial temperature range, and rich industrial I/O including 8× CAN-FD, this module brings RISC-V AI to the factory floor.

SpacemiT K3 Zhongda Tech Edge AI 60 TOPS Mini COM-E RVA23 Industrial 30B LLM

Overview: RISC-V AI at the Edge

Zhongda Tech (众达科技), a Chinese embedded systems specialist, partnered with SpacemiT (进迮时空) to build a fully domestic industrial edge AI module based on the K3 SoC. The module targets applications where data must stay on-premises — smart manufacturing, humanoid robotics, power-grid monitoring, and edge AI gateways — combining general-purpose RISC-V computing with on-die AI acceleration in a single chip.

The K3 is the world's first mass-produced RISC-V SoC to conform to the RVA23 profile, integrating 8 high-performance X100 CPU cores alongside 8 A100 AI cores. This "homogeneous fusion" architecture means both the host CPU and the AI accelerator speak the same RISC-V ISA, simplifying the software stack and eliminating cross-architecture data-movement overhead.

Full Specifications

Module Specifications
SoCSpacemiT K3 (RISC-V, RVA23 Profile)
CPU Cores8× X100 high-performance cores, up to 2.2 GHz
CPU Performance130 KDMIPS (general-purpose)
AI Cores8× A100 ultra-wide parallel RISC-V AI cores
AI Performance60 TOPS (general-purpose AI compute)
Vector Width1024-bit RVV 1.0 (RISC-V Vector extension)
Supported Data TypesBF16 / FP16 / FP8 / INT8 / INT4
Max LLM Size30B parameters (300 billion), runs locally
GraphicsIntegrated 3D graphics engine
Video CodecH.265 / H.264 decode, up to 4K@180fps
Memory32 GB LPDDR5 (domestic brand, on-board)
Crypto EngineInternational algorithms + Chinese commercial cryptography (SM2/SM3/SM4)
Form FactorMini COM-E (84 mm × 55 mm)
Power Consumption13 W (typical)
Temperature Range-40°C to +70°C (industrial grade)
Input Voltage4.5 V to 16 V (wide-range DC input)
Supply Chain100% domestic components, all-surface-mount design

Industrial I/O Interfaces

The module's I/O is tailored for industrial and robotics applications, with heavy emphasis on real-time control buses:

InterfaceCount / Detail
CAN-FD / CAN 2.0B8 channels (independent)
TTL Serial (UART)4 channels
I²C6 channels
Gigabit Ethernet2 ports (optical-electrical combo)
PCIePCIe 3.0 ×8
USB4× USB 2.0 (multiplexed with USB 3.0)
Type-CFull-function (data + display + power)
Camera Input2× 4-lane MIPI-CSI
Display OutputMultiple display outputs

Eight CAN-FD channels are particularly significant for multi-axis robotics — a single module can independently control up to 8 servo drives or joint motors without an external CAN expander, a configuration that is uncommon even among ARM-based industrial SoMs.

AI Software Stack

The module ships with a complete AI SDK designed for rapid deployment:

Operating system support includes standard Linux and Kylin V10 (银河࿤), the Chinese government-certified domestic OS, making the module suitable for Xinchuang (信创) procurement scenarios that mandate domestic software stacks.

Running a 30B Model on the Edge

The headline capability is local 30B-parameter LLM inference. The K3's 8 A100 AI cores support FP8 and INT4 quantization natively — a 30B model in INT4 requires approximately 15 GB of memory, which fits comfortably within the 32 GB LPDDR5 pool. The 1024-bit RVV 1.0 vector width enables wide SIMD-style parallelism across all 8 AI cores simultaneously.

For context, the K3's predecessor K1 (8× X60 cores, 2 TOPS AI) could only run small models (<1B). The K3 represents a 30× improvement in AI compute and an 80× increase in supported model size over the K1 — a generational leap that makes edge-deployed LLMs practical for the first time on RISC-V hardware.

Comparison: K1 vs. K3 vs. Module

ParameterSpacemiT K1SpacemiT K3Zhongda K3 Module
CPU Cores8× X60 @ 1.6 GHz8× X100 @ 2.2 GHz8× X100 @ 2.2 GHz
CPU IPC (SpecInt2k6/GHz)~4~9~9
AI Cores8× A1008× A100
AI Compute2 TOPS60 TOPS60 TOPS
RVV Width256-bit1024-bit1024-bit
Max LLM<1B30B30B (Qwen3-30B verified)
FP8 InferenceNoYes (native)Yes (native)
RVA23 ProfileNoYes (first mass-produced)Yes
Form FactorSoC onlySoC onlyMini COM-E 84×55 mm
TemperatureCommercialCommercial-40 to +70°C industrial
Power13 W typical
CAN-FD8 channels

Application Scenarios

Domestic Supply Chain Significance

The module is designed for China's Xinchuang (Information Technology Application Innovation) initiative, which mandates fully domestic supply chains for government and critical-infrastructure procurement. Key differentiators:

SpacemiT K3 SoC Architecture Context

The K3 SoC at the heart of this module was announced in January 2026 as the world's first mass-produced RISC-V chip conforming to the RVA23 profile. Its key architectural milestones:

SpacemiT's CPU core roadmap extends beyond K3: the X200 core (development complete, targeting 2027 mass production) reaches 16 SpecInt2k6/GHz — comparable to ARM's Neoverse N2 server core — with the next-generation X300 targeting 20/GHz. The AI core roadmap scales from A60 (2 TOPS, edge) → A100 (32 TOPS, desktop) → A200 (256 TOPS, server). On the SoC side, K3 is followed by K5 and K7 (edge), while the V-series (V100 taped out, V200 in development) targets datacenter servers.

Official Resources