OwnAI Compute
Book a call
NVIDIA Jetson · AGX Orin

Jetson AGX Orin 32GB

1792-core NVIDIA Ampere architecture GPU · 8-core Arm Cortex-A78AE, 2 MB L2 + 4 MB L3 · 32 GB 256-bit LPDDR5

Module price in your region
$2,697 excl. tax
Stock: 14

Manufacturer specifications

Processor architecture
NVIDIA Orin SoC, Arm v8.2 64-bit
CPU
8-core Arm Cortex-A78AE, 2 MB L2 + 4 MB L3
GPU
1792-core NVIDIA Ampere architecture with 56 Tensor Cores
AI performance
200 TOPS (INT8, sparse)
Memory
32 GB 256-bit LPDDR5
Memory bandwidth
204.8 GB/s
Storage
64 GB eMMC 5.1 · 2 M.2 NVMe slot(s) on our carrier
Networking
1× Gigabit Ethernet + 1× 10 Gigabit Ethernet
Power
15 W – 40 W (configurable power modes)
Dimensions
100 × 87 mm module; dev kit 110 × 110 × 71.65 mm
Cooling
Active thermal solution with fan
Expansion
PCIe Gen4 up to 2×8 + 1×4 + 2×1, USB 3.2 Gen2, 6 × 4-lane CSI, 1× 8K display
Supported frameworks
  • JetPack 6
  • CUDA 12
  • cuDNN
  • TensorRT
  • TensorRT-LLM (selected models)
  • PyTorch
  • ONNX Runtime
  • DeepStream
  • Isaac ROS
  • Ollama
  • llama.cpp
  • MLC
  • Docker

Source: NVIDIA product pages. Figures are manufacturer specifications, not our measurements.

Theoretical vs real-world

200 TOPS is a peak figure at INT8, sparse with structured sparsity. Chat-style LLM generation is limited by the 204.8 GB/s memory bus and by how much model fits in 32 GB. Rough rule: tokens/s ≈ bandwidth ÷ model bytes.

80
~3B INT4
estimated tokens/s
30
~8B INT4
estimated tokens/s
18
~13B INT4
estimated tokens/s

Estimates assume ~0.6 bytes/parameter at INT4 and ~70% achieved bandwidth. Real results vary by runtime.

Measured LLM inference

We only publish figures we or NVIDIA have measured. None are published yet for this module; use the estimates above for planning.

Rejoining the server...

Rejoin failed... trying again in seconds.

Failed to rejoin.
Please retry or reload the page.

The session has been paused by the server.

Failed to resume the session.
Please retry or reload the page.