Leetop Vast-XX Box
Nvidia Jetson Xavier / Orin
Take supercomputer performance to the edge.
Small Size. Small Price. Big AI Discoveries.
Leetop VAST BOX, based on discover the power of AI and robotics with NVIDIA® Jetson . It’s small, powerful, and priced for everyone . This means educators, students, and other enthusiasts can now easily create projects with fast and efficient AI using the entire GPU-accelerated NVIDIA software stack.
The Leetop VAST BOX benefits from new cloud-native support across the entire Jetson platform line-up, making it easier to build, manage, and deploy AI at the edge.
Pre-trained AI models from NVIDIA NGC together with the NVIDIA Transfer Learning Toolkit, provides a faster path to trained and optimized AI networks. Containerized deployment to Jetson devices also allows flexible and seamless updates.
NVIDIA JetPack™ SDK enables multi-modal AI application development for Leetop VAST BOX with accelerated libraries supporting all major AI frameworks, as well as computer vision, computer graphics, multimedia, and more. Together with the latest NVIDIA tools for application development and optimization, JetPack ensures fast time to market and reduced development costs.
Designed for ease of development and speed of deployment, Leetop is the most flexible and scalable platform to get to market and continuously update AI software over the lifetime of a product.
Interface
Interface | Specification |
|
Network | 2 x Gigabit Ethernet Connector (10/100/1000) |
|
Video Output | 2 x HDMI 2.0 (TYPE A) |
|
USB | 6 x USB 3.0 (TYPE A) + 1 x USB-OTG (Type C) |
|
Audio | 1 x Audio Jack (3.5mm) |
|
M.2 KEY M | 1x M.2 KEY M (NVMe SSD) |
|
TF Slot | 1 x TF Card Slot |
|
SIM Slot | 1 x SIM Card Slot |
|
Function Keys | 1 x Reset Button + 1 x Recovery Button + 1 x Power Button |
|
Serial port (Optional) | RS232 x 1 (2) / RS485 x 1 (2) / 1X SPI Bus(+3.3V Level) / 1x CAN /2x I2C Link (+3.3V I/O) 1x UART(+3.3V Level) / 1X SPI Bus(+3.3V Level) / 2x GPIO(+3.3V Level) |
|
KEY FEATURES
Processor | NVIDIA Jetson AGX Xavier | NVIDIA Jetson AGX Orin |
AI Performance | 32 TOPs | Up to 200 Sparse TOPS (INT8) |
GPU | 512-core Volta GPU with 64 Tensor Cores 11 TFLOPS (FP16) 22 TOPS (INT8) | 2 GPC/ 8 TPC/MIG/2048 NVIDIA® CUDA® cores / 64 Tensor cores Ray-Tracing cores/ End-to-end lossless compression / Tiled Caching / OpenGL® 4.6+ / OpenGL ES 3.2/ Vulkan™ 1.2+◊/ |
GPU Max Freq | 2200 MHz | 1 GHz |
CPU | 8-core Carmel ARM v8.2 64-bit CPU, 8MB L2 + 4MB L3 | Arm Cortex-A78AE |
CPU Max Freq | 4-core @ 2200MHz 6/8-core @ 1400MHz | 2 GHz |
Memory | 32GB 256-Bit LPDDR4x |136.5GB/s | 32 GB 256-bit LPDDR5 DRAM |
Storage | 32GB eMMC 5.1 | 64 GB eMMC 5.1 64 MB NOR Boot Flash 8 MB NOR Secure Key Flash |
Power | 10W |15W |30W | 5V and 20V |
PCIe | 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen4, Root Port & Endpoint) | PCI Express 4.0 x1, x2, x4 and x8 Up to 3x Endpoint supported |
CSI Camera | Up to 6 cameras (36 via virtual channels) 16 lanes MIPI CSI-2 |8 lanes SLVS-EC D-PHY 1.2 (up to 40 Gbps) C-PHY 1.1 (up to 62 Gbps) | 16×: CSI Lanes D-PHY v2.1 |
Video Encode | 2x1000MP/sec 4x 4K @ 60 (HEVC) 8x 4K @ 30 (HEVC) 16x 1080p @ 60 (HEVC) 32x 1080p @ 30 (HEVC) | 2×: 4K60 (H.265) /1x: 8K30 (H.265) |
Video Decode | 2x1500MP/sec 2x 8K @ 30 (HEVC) 6x 4K @ 60 (HEVC) 12x 4K @ 30 (HEVC) 26x 1080p @ 60 (HEVC) 52x 1080p @ 30 (HEVC) 30x 1080p @ 30 (H.264) | 2×: 4K60 (H.265) /1x: 8K30 (H.265) |
Display | 3 multi-mode DP 1.4/eDP 1.4/HDMI 2.0 No DSI support | 1×: shared HDMI™ 2.0, eDP1.4, VESA® DisplayPort™ (DP) HBR3 |
DL Accelerator | (2x) NVDLA Engines* |5 TFLOPS (FP16), 10 TOPS (INT8) | Deep Learning Accelerator (DLA) / Up to 90 INT8 TOPS (Deep Learning Inference) / 2MB dedicated SRAM |
Vision Accelerator | 7-way VLIW Vision Processor* | Programmable Vision Accelerator (PVA) / Up to 512 INT16 GMACS or 2048 INT8 GMACS / 2MB dedicated SRAM |
Networking | 10/100/1000 BASE-T Ethernet | RGMII |
Mechanical | 100 mm x87 mm 699-pin connector Integrated Thermal Transfer Plate | 100.0 mm x 87.0 mm x 16.0 mm 699 pin B2B Connector Integrated Thermal Transfer Plate (TTP) with Heatpipe |
Install Dimension