NVIDIA Jetson · Orin Nano
Jetson Orin Nano 8GB
1024-core NVIDIA Ampere architecture GPU · 6-core Arm Cortex-A78AE, 1.5 MB L2 + 4 MB L3 · 8 GB 128-bit LPDDR5
Manufacturer specifications
- Processor architecture
- NVIDIA Orin SoC, Arm v8.2 64-bit
- CPU
- 6-core Arm Cortex-A78AE, 1.5 MB L2 + 4 MB L3
- GPU
- 1024-core NVIDIA Ampere architecture with 32 Tensor Cores
- AI performance
- 67 TOPS (INT8, sparse (Super mode))
- Memory
- 8 GB 128-bit LPDDR5
- Memory bandwidth
- 102 GB/s
- Storage
- None on module; boots from NVMe · 2 M.2 NVMe slot(s) on our carrier
- Networking
- 1× Gigabit Ethernet; M.2 Key E for Wi-Fi
- Power
- 7 W – 25 W (configurable power modes)
- Dimensions
- 69.6 × 45 mm module; dev kit 100 × 79 × 21 mm
- Cooling
- Active heatsink with fan for 25 W Super mode
- Expansion
- PCIe Gen3 1×4 + 3×1, 4× USB 3.2 Gen2, 2× 4-lane CSI, M.2 Key M ×2, M.2 Key E
- 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
67 TOPS is a peak figure at INT8, sparse (Super mode) with structured sparsity. Chat-style LLM generation is limited by the 102 GB/s memory bus and by how much model fits in 8 GB. Rough rule: tokens/s ≈ bandwidth ÷ model bytes.
40
~3B INT4
estimated tokens/s
15
~8B INT4
estimated tokens/s
—
~13B INT4
does not fit
Estimates assume ~0.6 bytes/parameter at INT4 and ~70% achieved bandwidth. Real results vary by runtime.
Measured LLM inference
| Model | Quantisation | Runtime | Tokens/s |
|---|---|---|---|
| Llama 3.1 8B NVIDIA-published Super mode figure | INT4 | MLC, Super mode | 19.1 |
| Llama 3.2 3B NVIDIA-published Super mode figure | INT4 | MLC, Super mode | 43.1 |
| Qwen2.5 7B NVIDIA-published Super mode figure | INT4 | MLC, Super mode | 21.8 |
| Gemma 2 2B NVIDIA-published Super mode figure | INT4 | MLC, Super mode | 35 |
| Phi 3.5 3B NVIDIA-published Super mode figure | INT4 | MLC, Super mode | 38.1 |