跳到主要内容Skip to main content

← 返回硬件算力← Back to Compute

边缘设备Edge devices

NVIDIA Jetson AGX Orin 64GBNVIDIA Jetson AGX Orin 64GB

回答机器人本体上「板端能跑多大模型」的内存与算力上限。不回答实际帧率:TOPS 是官方标称口径,真实推理速度取决于量化方式、输入分辨率与散热条件,需要实测才有结论。Answers the on-board memory and compute ceiling that decides how large a model a robot body can run. It does not answer real frame rates: TOPS is a vendor rating, and actual inference speed depends on quantisation, input resolution and thermal headroom, which only measurement can settle.

关键参数Key specs

AI performance
275 TOPS
GPU
2048-core Ampere, 64 Tensor Cores
CPU
12-core Arm Cortex-A78AE
memory
64 GB LPDDR5, 256-bit
memory bandwidth
204.8 GB/s
power
15 W - 60 W
module size
100 mm x 87 mm
storage
64 GB eMMC 5.1

官方原文怎么说What the source says

Jetson AGX Orin modules deliver up to 275 TOPS of AI performance with power configurable between 15W and 60W.
1 https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/
Memory 64GB 256-bit LPDDR5 204.8GB/s
2 https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/

资料与许可Source and licence

资料时间Source checked
2026-11-07
许可 / 类型Licence / kind
official-spec-page
许可说明Licence evidence
https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/
类目Category
边缘设备Edge devices

去官网看原页Open the official page →

← 返回硬件算力← Back to Compute