嵌入式开发文档
  • Jetson Nano 系列：面向入门级边缘计算，提供 2GB 和 4GB 版本，AI 性能约为 472 GFLOPS。
  • Jetson TX 系列：如 TX2、TX2i，属于早期嵌入式模块，广泛应用于工业与小型化部署。
  • Jetson Xavier 系列：包含 Jetson Xavier NX 及 Jetson AGX Xavier，AI 性能在 21 至 32 TOPS 之间。
  • Jetson Orin 系列：当前主流的高性能边缘 AI 平台，包含 Orin Nano、Orin NX 以及 AGX Orin，算力最高可达 275 TOPS。
  • Jetson AGX Thor 系列：基于最新的 Blackwell 架构，是性能大幅提升的新一代边缘计算核心板。

模组发布列表

Year Name GPU CPU Memory Power
2014 Jetson TK1 192-core Nvidia Kepler architecture GPU Quad-core ARM Cortex-A15 processor 2 GiB 10 W
2015 Jetson TX1 256-core Nvidia Maxwell architecture GPU Quad-core ARM Cortex-A57 MPCore processor 4 GiB 10 W
2017 Jetson TX2 256-core Nvidia Pascal architecture GPU Dual-core Nvidia Denver 2 64-bit CPU and quad-core ARM Cortex-A57 MPCore processor 8 GiB 7.5–15 W
2018 Jetson AGX Xavier 512-core Nvidia Volta architecture GPU with 64 Tensor cores 8-core NVIDIA Carmel ARMv8.2 64-bit CPU 8MB L2 + 4MB L3 32–64 GiB 10-40 W
2019 Jetson Nano 128-core Nvidia Maxwell architecture GPU Quad-core ARM Cortex-A57 MPCore processor 4 GiB 5–10 W
2020 Jetson Xavier NX 384-core Nvidia Volta architecture GPU with 48 Tensor cores 6-core Nvidia Carmel ARMv8.2 64-bit CPU 6MB L2 + 4MB L3 8 GiB 10–20 W
2023 Jetson Orin Nano up to 1024-core Nvidia Ampere architecture GPU with 32 Tensor cores 6-core ARM Cortex-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 4–8 GiB 7–25 W
2023 Jetson Orin NX 1024-core Nvidia Ampere architecture GPU with 32 Tensor cores up to 8-core ARM Cortex-A78AE v8.2 64-bit CPU 2MB L2 + 4MB L3 8–16 GiB 10–40 W
2023 Jetson AGX Orin up to 2048-core Nvidia Ampere architecture GPU with 64 Tensor cores up to 12-core ARM Cortex-A78AE v8.2 64-bit CPU 3MB L2 + 6MB L3 32–64 GiB 15–60 W
2025 Jetson AGX Thor 2560-core Nvidia Blackwell architecture GPU with 96 Tensor cores 14-core ARM Neoverse-V3AE 64-bit CPU 1MB L2 + 16MB L3 128 GiB 130 W

核心架构

Maxwell architecture

Mode 0 1
GPU clock (MHz) 921 640
Cortex-A57 (MHz) 4x 1428 2x 918
2x stopped
TDP (W) 10 5

Pascal architecture

JetsonTX2 SeriesComparisonTable

ProductName GPUPerformance
DenseTensor
FP16TFLOPS		 Memory
GB		 Storage
GB		 Power
W
Jetson TX2 NX 1.33 4 16 7.5, 15
Jetson TX2 4GB 1.33 4 16 7.5, 15
Jetson TX2i 1.26 8 32 10, 20
Jetson TX2 1.33 8 32 7.5, 15

Volta architecture

JetsonXavierSeriesComparisonTable

ProductName GPUPerformance
DenseTensor
INT8TOPS		 DLAPerformance
DenseTensor
INT8TOPS		 Memory
GB		 Storage
GB		 Power
W
Jetson Xavier NX 13 8 8 16 10, 15, 20
Jetson Xavier NX 16GB 13 8 16 16 10, 15, 20
Jetson AGX Xavier 22 10 32 32 10, 15, 30
Jetson AGX Xavier Industrial 20 10 32 32 20, 40
Jetson AGX Xavier 64GB 22 10 64 64 10, 15, 30

Ampere architecture

JetsonOrinSeriesComparisonTable

ProductName GPUPerformance
DenseTensor
INT8TOPS		 DLAPerformance
DenseTensor
INT8TOPS		 Memory
GB		 Storage
GB		 Power
W
Jetson Orin Nano 4GB 17 —N/a 4 —N/a 7, 10, 25
Jetson Orin Nano 8GB 33 —N/a 8 —N/a 7, 15, 25
Jetson Orin NX 8GB 38 20 8 —N/a 10, 15, 25, 40
Jetson Orin NX 16GB 38 40 16 —N/a 10, 15, 25, 40
Jetson AGX Orin 32GB 54 46 32 64 15, 40
Jetson AGX Orin Industrial 78 46 64 64 15, 75
Jetson AGX Orin 64GB 85 52.5 64 64 15, 60

Jetson TX2

  • GPU: Pascal 架构，256 个 CUDA 核心
  • CPU: 4 核 Cortex-A57 + 2 核 Denver 2
  • 内存: 8GB LPDDR4
  • 算力: 1.3 TOPS (FP16)
  • 功耗: 7.5-15W

Jetson Nano

Jetson Nano是Nvidia在TX2和Xavier获得成功后推出的低配版GPU运算平台。

  • GPU: Maxwell 架构，128 个 CUDA 核心
  • CPU: 4 核 ARM Cortex-A57
  • 内存: 4GB LPDDR4
  • 算力: 0.5 TOPS (INT8)
  • 功耗: 5-10W

Jetson Nano有两个版本A02和B01。

  • A02 (Original Version): Features a single MIPI CSI camera connector and part number 945-13450-0000-000.
  • B01 (Updated Version): Adds a second MIPI CSI camera connector to support stereo/dual cameras and updates the pin placement, using part number 945-13450-0000-100.

Jetson Xavier NX

  • GPU: Volta 架构，384 个 CUDA 核心，48 个 Tensor 核心
  • CPU: 6 核 ARM Cortex-A57
  • 内存: 8GB 或 16GB LPDDR4x
  • 算力: 21 TOPS (INT8)
  • 功耗: 10-15W

Jetson AGX Xavier

  • GPU: Volta 架构，512 个 CUDA 核心，64 个 Tensor 核心
  • CPU: 8 核 ARM v8.2 + 2 核 NVDLA
  • 内存: 16GB LPDDR4
  • 算力: 32 TOPS (INT8)
  • 功耗: 10-30W

Jetson Orin NX

  • GPU: Ampere 架构，1536 个 CUDA 核心，48 个 Tensor 核心
  • CPU: 8 核 ARM Cortex-A78AE
  • 内存: 8GB 或 16GB LPDDR5
  • 算力: 70 TOPS 或 100 TOPS (INT8)
  • 功耗: 10-25W

Jetson AGX Orin

  • GPU: Ampere 架构，2048 个 CUDA 核心，64 个 Tensor 核心
  • CPU: 12 核 ARM Cortex-A78AE
  • 内存: 32GB 或 64GB LPDDR5
  • 算力: 200 TOPS (INT8)
  • 功耗: 15-60W