Beijing Plink AI Technology Co., Ltd
Beijing Plink AI is an expert of cloud-to-end one-stop solution.
Add to Cart
| AI Performance | Up to 70 (Sparse) INT8 TOPs and 35 (Dense) INT8 TOPs |
| Ampere GPU | 1024 NVIDIA® CUDA® cores | 32 Tensor cores | End-to-end lossless compression | Tile Caching | OpenGL® 4.6 | OpenGL ES 3.2 | Vulkan™ 1.1 ◊ | CUDA 10 |
| Deep Learning Accelerator | 1x NVDLA |
| Maximum Operating Frequency | 610 MHz | 20 TOPs (Sparse INT8) |
| ARM Cortex-A78AE CPU | Eight-core (ONX 16GB) or six-core (ONX 8GB) Cortex A78AE ARMv8.2 (64-bit) heterogeneous multi-processing (HMP) CPU architecture | 2x clusters (4x 256KB L2 +2MB L3) + 4MB LLC | L3 Cache: 4 MB (shared across all clusters) |
| Audio | Dedicated programmable audio processor | ARM Cortex A9 with NEON | PDM in/out | Industry-standard High-Definition Audio (HDA) controller provides a multi-channel audio path to the HDMI® interface |
| Memory | 8 GB 128-bit LPDDR5 DRAM |
| Networking | 10/100/1000 BASE-T Ethernet | Media Access Controller (MAC) |
| Imaging | Eight lanes MIPI CSI-2 | D-PHY 2.1 (20 Gbps) |
| Display Controller | 1x shared HDMI 2.1, eDP 1.4, VESA DisplayPort 1.4a HBR3 |
| Maximum Resolution (eDP/DP/HDMI) | up to 3840x2160 at 60 Hz (up to 36 bpp) | up to four displays can be supported over DP interface with MST and compatible serializer |
| Storage | Supports External Storage (NVMe) via x1 PCIe |
| Module | CUDA Cores | Tensor Cores | Operating Frequency per Core (up to) |
| Jetson Orin NX 16GB | 1024 | 32 | 918 MHz |
| Jetson Orin NX 8GB | 1024 | 32 | 765 MHz |
