NVIDIA Jetson AGX Orin 32GB Module
- AI Performance:
- Up to 200 TOPS
- Memory:
- 32GB LPDDR5
- Form Factor:
- 699-pin board-to-board connector
Consumercarts is reader-supported. Learn more
Disclaimer: The price and specification of the given product may differ from the actual product. Please confirm on the retailer's website before buying.
Manufacturer: NVIDIA Last updated: 2026-09-15
Where to buy
- NVIDIAGo to store
NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5) Review
NVIDIA Jetson AGX Orin 32GB production compute module delivering up to 200 TOPS of AI performance for embedding into custom carrier boards in robotics and autonomous machines.
The 32GB AGX Orin module is the mid-tier variant of NVIDIA's flagship Orin lineup, giving OEMs most of the 64GB module's Ampere GPU compute at a lower memory footprint and price.
Specifications
Identity
| Brand | NVIDIA |
|---|
Processor
| CPU Cores | 12 cores |
|---|
| CPU Architecture | ARM |
|---|---|
| Memory | 32 GB |
| Storage Type | NVMe/M.2 |
| Has AI Accelerator / NPU | Yes |
| GPIO Header | No |
| Use Case | AI / Machine Learning |
| SoC | NVIDIA Jetson AGX Orin |
| Memory Options | 32GB LPDDR5, 256-bit |
| NPU Performance (TOPS) | Up to 200 TOPS INT8 (with 2x NVDLA v2) |
| GPU | 1792-core NVIDIA Ampere GPU with 56 Tensor Cores |
| OS Support | NVIDIA JetPack (Ubuntu-based Linux for Tegra) |
| Board Size | 100mm x 87mm (module) |
| Board Revision | Production Module (32GB) |
Expert Review
Reviewed by Burooj Alam. Rated by us, not by users.
Best for
- OEM autonomous machine products
- High-performance edge AI appliances
Not for
- Plug-and-play use without a carrier board
- Memory-heavy multi-model AI pipelines
FAQs
What are the key specifications of the NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)?
The NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5) is a single board computer from NVIDIA. Key specs: SoC NVIDIA Jetson AGX Orin, CPU Architecture ARM, CPU Cores 12, Memory 32, Memory Options 32GB LPDDR5, 256-bit.
Will the NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5) work with my current setup?
The NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5) lists SoC is NVIDIA Jetson AGX Orin. Check that against the hardware you already own before buying, since this is the field that most often decides whether a part fits.
Who is the NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5) best suited to?
It suits oem autonomous machine products, high-performance edge ai appliances.
What are the drawbacks of the NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)?
It is a poor fit for plug-and-play use without a carrier board, memory-heavy multi-model ai pipelines.
Compare and read more
- Banana Pi BPI-R4 (Single-Board Computer/MediaTek Filogic 880/Quad-Core Cortex-A73/WiFi 7/10GbE Router Board) vs NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)
- BeagleBone AI-64 (Single-Board Computer/Texas Instruments TDA4VM/Dual-Core Cortex-A72 2.0GHz/4GB RAM/Robotics and Vision AI Pick) vs NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)
- ClockworkPi uConsole (Handheld Computer/Raspberry Pi CM4 or RK3566 Core/Clamshell Keyboard and Screen/Modular SBC Terminal) vs NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)
- FriendlyElec NanoPC-T6 (Single-Board Computer/Rockchip RK3588/Octa-Core/Up to 16GB LPDDR5/Dual 2.5GbE and M.2 NVMe) vs NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)
- FriendlyElec NanoPi NEO3 (Single-Board Computer/Rockchip RK3328/Quad-Core Cortex-A53 1.29GHz/Gigabit Ethernet) vs NVIDIA Jetson AGX Orin 32GB Module (Compute Module/12-Core Cortex-A78AE/1792-Core Ampere GPU/Up to 200 TOPS/32GB LPDDR5)