M.2 AI Inference Acceleration card
Edge

M.2 AI Inference Acceleration card

Axelera AI

Overview

AI accelerator module designed for edge deployment with high efficiency neural processing. Optimized for computer vision and inference workloads at the edge with minimal power consumption.

Key Features

  • Integrated neural processing unit
  • Optimized for edge deployment
  • Enterprise-ready configuration

Ideal For

developers and startups deploying AI inference at the edge for computer vision, robotics, and IoT applications.

Form Factor

M.2 2280 M-key

Host Interface

PCIe Gen3 x4 – 4 GB/s bidirectional

AIPU (AI Processing Unit)

1x Metis AIPU

AIPU Memory

1 GB DRAM

Peak INT8 TOPS

214

Operating temperature

-20 to +70°C

Thermal solution

Optional standalone active cooling

Typical Application Power

3.5-9 W

Security Features

Secure Boot, Root of Trust

$249.95

Prices may vary. Verify on vendor site.

View on Axelera AI →

Quick Specs

Form Factor
M.2 2280 M-key
Host Interface
PCIe Gen3 x4 – 4 GB/s bidirectional
AIPU (AI Processing Unit)
1x Metis AIPU
AIPU Memory
1 GB DRAM
Peak INT8 TOPS
214
Operating temperature
-20 to +70°C

Tags

computer-visionllm-inference