Autonomous Machines & Robotics
- Autonomous Mobile Robots (AMR)
- Humanoid & Heavy Industrial Robotics
Product Code: Jetson-AGX-Orin-32GB
NVIDIA Jetson AGX Orin 32GB SOM | Ampere Architecture GPU, 8-Core Arm Cortex-A78AE CPU, 32GB LPDDR5, Up to 200 TOPS AI Performance
NVIDIA Jetson AGX Orin 32GB SOM | Ampere Architecture GPU, 8-Core Arm Cortex-A78AE CPU, 32GB LPDDR5, Up to 200 TOPS AI Performance
-
Need volume pricing or a formal corporate quotation?
Primary Use Cases
Professional Workflows And Applications
Edge AI & Computer Vision
- Real-Time Video Analytics
- Multi-Camera AI Vision Systems
Edge Computing & HPC
- Multi-Sensor Fusion & Perception
- Edge Deep Learning Inference
Healthcare & Industrial Automation
- Real-Time Medical Imaging Devices
- Smart Factory Quality Inspection
NVIDIA Jetson AGX Orin 32GB System-on-Module (SOM)
Overview & Value Proposition
The NVIDIA Jetson AGX Orin 32GB System-on-Module (SOM) provides cost-effective, high-performance embedded AI processing for autonomous robotics, computer vision, and high-density edge deployments. Powered by the NVIDIA Ampere GPU architecture and an 8-core Arm Cortex-A78AE CPU, it delivers up to 200 INT8 TOPS of AI compute within a flexible 15W to 40W power profile. Featuring 32GB of unified LPDDR5 memory and dedicated hardware accelerators, the module offers an ideal balance of compute density and memory capacity for real-time sensor processing and edge AI workflows.
ย
Key Features & Business Benefits
-
Ampere GPU Architecture with 200 INT8 TOPS: Features a 1792-core NVIDIA Ampere GPU with 56 3rd-Gen Tensor Cores, delivering up to 200 INT8 TOPS (or 100 dense INT8 TOPS / 50 FP16 TFLOPS) to accelerate localized AI inference.
-
8-Core Arm Cortex-A78AE CPU: Driven by a 64-bit 8-core Arm CPU cluster running up to 2.2 GHz to execute real-time application code, ROS 2 nodes, and control logic alongside GPU tasks.
-
32GB Unified LPDDR5 System Memory: 256-bit memory subsystem providing 204.8 GB/s bandwidth across a shared pool for high-resolution camera feeds, vision models, and deep learning pipelines.
-
Dual NVDLA v2.0 & PVA v2.0 Accelerators: Dedicated Deep Learning Accelerators and a Programmable Vision Accelerator engine offload computer vision tasks and neural network execution from the main GPU.
-
Configurable Power Modes (15Wโ40W): Software-configurable TDP options (15W, 25W, and 40W) allow operational deployment within strict battery, thermal, and enclosure limits.
-
High-Speed I/O & Sensor Connectivity: Supports 10GbE networking, PCIe Gen 4 lanes, USB 3.2 Gen 2 ports, and up to 16 MIPI CSI-2 camera lanes for multi-sensor integration.
-
NVIDIA JetPack & Software Stack Support: Fully integrated with NVIDIA JetPack SDK, Isaac robotics framework, Metropolis vision platform, and CUDA-X libraries for cloud-to-edge software deployment.
ย
Who Is This For?
Autonomous Mobile Robot (AMR) Developers
For teams engineering commercial AMRs, logistics robots, and agricultural machinery requiring multi-camera perception and path planning within an economical hardware budget.
Edge Vision & Analytics System Integrators
For developers deploying real-time multi-stream video analytics, smart retail tracking, and automated industrial quality control nodes.
Medical Device & Inspection Equipment Manufacturers
For OEMs building AI-assisted medical imaging devices, diagnostic equipment, and high-throughput optical inspection machinery.
Smart Infrastructure Operators
For organizations installing edge computing nodes for traffic monitoring, security analytics, and smart city infrastructure.
ย
Frequently Asked Questions (FAQ)
Q: What is the main difference between the Jetson AGX Orin 32GB and 64GB SOM models?
A: The AGX Orin 32GB SOM features 32GB LPDDR5 memory, an 8-core CPU, 1792 CUDA cores, and up to 200 INT8 TOPS of AI performance within a 15Wโ40W envelope. The 64GB model doubles system VRAM to 64GB, increases CPU cores to 12, features 2048 CUDA cores, and reaches up to 275 INT8 TOPS at up to 60W TDP.
Q: Is the Jetson AGX Orin 32GB SOM pin-compatible with other AGX Orin modules?
A: Yes. It shares the identical 100mm x 87mm form factor and 699-pin Molex Mirror Mezzanine connector standard across the AGX Orin family, allowing drop-in compatibility with existing carrier boards.
Q: Does the 32GB SOM include built-in eMMC storage?
A: Yes. The module includes 64GB of onboard eMMC 5.1 storage for operating system images and system files, with external NVMe SSD storage expansion supported via PCIe Gen 4 lanes on the carrier board.
Q: What camera configurations are supported by the module?
A: The module natively supports up to 16 MIPI CSI-2 lanes, accommodating up to 6 direct physical camera inputs or up to 16 virtual channel streams.
Q: Can I request a formal quotation for procurement?
A: Yes, we issue formal quotation documents with complete pricing, tax breakdowns, and payment terms for corporate or institutional procurement processes.
Q: Do you provide GST invoices?
A: Yes, we provide valid GST invoices for all orders. You can enter your GSTIN during checkout or provide it with your order details to claim input tax credit.
Q: Do you deliver across India?
A: Yes, we deliver to pincodes across all states and union territories in India through our logistics partners.
Q: Can I request availability and lead time before ordering?
A: Yes, you can contact us with your product requirements and quantity to confirm current stock availability and estimated delivery timelines before placing your order.
Description
Description
NVIDIA Jetson AGX Orin 32GB System-on-Module (SOM)
Overview & Value Proposition
The NVIDIA Jetson AGX Orin 32GB System-on-Module (SOM) provides cost-effective, high-performance embedded AI processing for autonomous robotics, computer vision, and high-density edge deployments. Powered by the NVIDIA Ampere GPU architecture and an 8-core Arm Cortex-A78AE CPU, it delivers up to 200 INT8 TOPS of AI compute within a flexible 15W to 40W power profile. Featuring 32GB of unified LPDDR5 memory and dedicated hardware accelerators, the module offers an ideal balance of compute density and memory capacity for real-time sensor processing and edge AI workflows.
ย
Key Features & Business Benefits
-
Ampere GPU Architecture with 200 INT8 TOPS: Features a 1792-core NVIDIA Ampere GPU with 56 3rd-Gen Tensor Cores, delivering up to 200 INT8 TOPS (or 100 dense INT8 TOPS / 50 FP16 TFLOPS) to accelerate localized AI inference.
-
8-Core Arm Cortex-A78AE CPU: Driven by a 64-bit 8-core Arm CPU cluster running up to 2.2 GHz to execute real-time application code, ROS 2 nodes, and control logic alongside GPU tasks.
-
32GB Unified LPDDR5 System Memory: 256-bit memory subsystem providing 204.8 GB/s bandwidth across a shared pool for high-resolution camera feeds, vision models, and deep learning pipelines.
-
Dual NVDLA v2.0 & PVA v2.0 Accelerators: Dedicated Deep Learning Accelerators and a Programmable Vision Accelerator engine offload computer vision tasks and neural network execution from the main GPU.
-
Configurable Power Modes (15Wโ40W): Software-configurable TDP options (15W, 25W, and 40W) allow operational deployment within strict battery, thermal, and enclosure limits.
-
High-Speed I/O & Sensor Connectivity: Supports 10GbE networking, PCIe Gen 4 lanes, USB 3.2 Gen 2 ports, and up to 16 MIPI CSI-2 camera lanes for multi-sensor integration.
-
NVIDIA JetPack & Software Stack Support: Fully integrated with NVIDIA JetPack SDK, Isaac robotics framework, Metropolis vision platform, and CUDA-X libraries for cloud-to-edge software deployment.
ย
Who Is This For?
Autonomous Mobile Robot (AMR) Developers
For teams engineering commercial AMRs, logistics robots, and agricultural machinery requiring multi-camera perception and path planning within an economical hardware budget.
Edge Vision & Analytics System Integrators
For developers deploying real-time multi-stream video analytics, smart retail tracking, and automated industrial quality control nodes.
Medical Device & Inspection Equipment Manufacturers
For OEMs building AI-assisted medical imaging devices, diagnostic equipment, and high-throughput optical inspection machinery.
Smart Infrastructure Operators
For organizations installing edge computing nodes for traffic monitoring, security analytics, and smart city infrastructure.
ย
Frequently Asked Questions (FAQ)
Q: What is the main difference between the Jetson AGX Orin 32GB and 64GB SOM models?
A: The AGX Orin 32GB SOM features 32GB LPDDR5 memory, an 8-core CPU, 1792 CUDA cores, and up to 200 INT8 TOPS of AI performance within a 15Wโ40W envelope. The 64GB model doubles system VRAM to 64GB, increases CPU cores to 12, features 2048 CUDA cores, and reaches up to 275 INT8 TOPS at up to 60W TDP.
Q: Is the Jetson AGX Orin 32GB SOM pin-compatible with other AGX Orin modules?
A: Yes. It shares the identical 100mm x 87mm form factor and 699-pin Molex Mirror Mezzanine connector standard across the AGX Orin family, allowing drop-in compatibility with existing carrier boards.
Q: Does the 32GB SOM include built-in eMMC storage?
A: Yes. The module includes 64GB of onboard eMMC 5.1 storage for operating system images and system files, with external NVMe SSD storage expansion supported via PCIe Gen 4 lanes on the carrier board.
Q: What camera configurations are supported by the module?
A: The module natively supports up to 16 MIPI CSI-2 lanes, accommodating up to 6 direct physical camera inputs or up to 16 virtual channel streams.
Q: Can I request a formal quotation for procurement?
A: Yes, we issue formal quotation documents with complete pricing, tax breakdowns, and payment terms for corporate or institutional procurement processes.
Q: Do you provide GST invoices?
A: Yes, we provide valid GST invoices for all orders. You can enter your GSTIN during checkout or provide it with your order details to claim input tax credit.
Q: Do you deliver across India?
A: Yes, we deliver to pincodes across all states and union territories in India through our logistics partners.
Q: Can I request availability and lead time before ordering?
A: Yes, you can contact us with your product requirements and quantity to confirm current stock availability and estimated delivery timelines before placing your order.
