NVIDIA Jetson Thor - NVIDIA -Macnica

Product Summary

NVIDIA® Jetson Thor™ delivers the highest performance for physical AI and robotics.

Supports a wide range of generative AI models, from Vision Language Action (VLA) models such as NVIDIA Isaac ™ GR00T for humanoids to all popular LLMs and VLMs to power the next generation of physics AI applications.
It runs the NVIDIA AI software stack for physical AI applications, including NVIDIA Isaac for robotics, NVIDIA Metropolis for visual agent AI, and NVIDIA Holoscan for sensor processing.
You can also build AI agents at the edge using NVIDIA agent AI workflows such as the Video Search and Summarization (VSS) Agent.

NVIDIA Jetson T5000 module

The NVIDIA Jetson T5000 series system module products are powered by the NVIDIA Blackwell architecture GPU with Transformer Engine and Multi-Instance GPU (MIG) to easily run the latest generative AI models. The 14-core Arm® Neoverse®-V3AE CPU, 4x 25 GbE networking, and extensive I/O options for sensor fusion accelerate real-time multi-sensor applications with low latency.
With up to 2070 FP4 TFLOPS of AI computing power and 128 GB of memory, it delivers over 7.5x the AI computing power of NVIDIA® AGX Orin™ and is 3.5x more energy efficient, making it the ultimate platform for humanoid robotics.

NVIDIA Jetson T4000 module

The NVIDIA Jetson T4000 series system module products are equipped with an NVIDIA Blackwell architecture GPU with Transformer Engine and Multi-Instance GPU (MIG), easily running the latest generative AI models. The 14-core Arm Neoverse-V3AE CPU, 3x 25 GbE networking, and extensive I/O options for sensor fusion accelerate real-time multi-sensor applications with low latency. With up to 1200 FP4 TFLOPS of AI computing power and 64 GB of memory, it delivers more than four times the AI computing power of NVIDIA AGX Orin, making it the ultimate platform for humanoid robotics.

NVIDIA Jetson AGX Thor Developer Kit

The NVIDIA Jetson AGX Thor Developer Kit is the ultimate platform for humanoid robotics, offering outstanding performance and scalability. It offers extensive I/O options, including 4x25GbE QSFP slots, wired multi-GbE RJ45 connectors, multiple USB ports, and additional connectivity interfaces.
With massive AI performance and sensor capabilities in a compact form factor, the Jetson AGX Thor Developer Kit is the ideal platform for developers looking to unlock new possibilities in humanoid robotics and other physical AI applications.

Product Specifications

NVIDIA Jetson Thor Module Specification Table

	Jetson T5000	Jetson T4000
GPUs	2560-core NVIDIA Blackwell architecture GPU with 96 fifth-gen Tensor Cores Multi-Instance GPU with 10 TPCs	1536-core NVIDIA Blackwell architecture GPU with fifth-gen Tensor Cores Multi-Instance GPU (MIG) with 6 TPCs
CPU	14-core Arm® Neoverse®-V3AE 64-bit CPU 64 KB I-Cache, 64 KB D-Cache 1 MB L2 Cache per core 16 MB shared system L3 cache	12-core Arm® Neoverse®-V3AE 64-bit CPU 1 MB L2 cache per core 16 MB shared system L3 cache
Memory	128 GB 256-bit LPDDR5X 273 GB/s	64 GB 256-bit LPDDR5X 273 GB/s
Storage	Supports NVMe through PCIe Supports SSD through USB3.2	Supports NVMe through PCIe Supports SSD through USB3.2
Encode	2x NVENCODE	2x NVENCODE
Decode	2x NVENCODE	2x NVENCODE
camera	Up to 20 cameras via HSB Up to 6 cameras through 16x lanes MIPI CSI-2 Up to 32 cameras using virtual channels C-PHY 2.1 (10.25 Gbps) D-PHY 2.1 (40 Gbps)	Up to 20 cameras via HSB Up to 6 cameras through 16x lanes MIPI CSI-2 Up to 32 cameras using Virtual Channels C-PHY 2.1 (10.25 Gbps) D-PHY 2.1 (40 Gbps)
Mechanical	100 mm x 87 mm 699-pin B2B connector Integrated Thermal Transfer Plate (TTP) with heatpipe	100 mm x 87 mm 699-pin B2B connector Integrated Thermal Transfer Plate (TTP) with heatpipe

NVIDIA Jetson AGX Thor Developer Kit Specification

	Jetson AGX Thor
	Jetson AGX Thor
AI Performance	2070 TFLOPS (FP4)
GPUs	2560-core NVIDIA Blackwell architecture GPU with 96 fifth-gen Tensor Cores
CPU	14-core Arm® Neoverse® V3AE 64-bit CPU 64 KB I-Cache, 64 KB D-Cache 1 MB L2 cache per core 16 MB shared system L3 cache
Memory	128 GB 256-bit LPDDR5X 273 GB/s
Storage	Supports NVMe through PCIe Supports SSD through USB3.2
Video Encode	6x 4Kp60 (H.265) 12x 4Kp30 (H.265) 24x 1080p60 (H.265) 50x 1080p30 (H.265) 48x 1080p30 (H.264) 6x 4Kp60 (H.264)
Video Decode	4x 8Kp30 (H.265) 10x 4Kp60 (H.265) 22x 4Kp30 (H.265) 46x 1080p60 (H.265) 92x 1080p30 (H.265) 82x 1080p30 (H.264) 4x 4Kp60 (H.264)
camera	Up to 20 cameras via HSB Up to 6 cameras through 16x lanes MIPI CSI-2 Up to 32 cameras using virtual channels C-PHY 2.1 (10.25 Gbps) D-PHY 2.1 (40 Gbps)
Ethernet	4x 25 GbE
Wi-Fi/BT	Requires external chip
Max Camera Support	6 cameras(32 via virtual channels)
Display	4x shared HDMI2.1 VESA DisplayPort 1.4a—HBR2, MST
# of Simutaneous Displays	4
UPHY (PCIe, USB)	Up to 8 lanes—Gen5 Root port only—C1 (x1) and C3 (x2) Root Point or Endpoint—C2 (x1), C4 (x8) and C5 (x4) xHCI host controller with integrated PHY 3x USB 3.2 4x USB 2.0
SATA and SDIO	-
Other I/Os	5x I2S/2x Audio Hub (AHUB), 2x DMIS, 4x UART, 4x CAN, 3x SPI, 13x I2C, 6x PWM outputs
Power	40 W–130 W