NVIDIA Jetson T4000
NVIDIA Jetson T4000 is a production system-on-module (SoM) from the Jetson Thor family. It pairs a 1536-core Blackwell-architecture GPU with fifth-generation Tensor Cores and a 12-core Arm Neoverse-V3AE CPU, reaching up to 1200 TFLOPS at FP4 (sparse) precision.
The module carries 64 GB of LPDDR5X memory (256-bit, 273 GB/s) and supports Multi-Instance GPU (MIG). It is the lower-tier Jetson Thor variant relative to the T5000 module (fewer GPU cores, half the memory, a lower power budget). It targets robotics, physical AI, and multi-sensor processing at the edge, with configurable power in the 40–70 W range.
Classification
AI System-on-Chip (SoC) · serves as: High-level compute, AI Inference, Computer vision processing, Embedded main processor.
Which group NVIDIA Jetson T4000 belongs to and how it is built
Compute Modules is a subcategory of hardware components that provide processing power for robotic systems. It encompasses onboard computers, single-board computers (SBCs), AI accelerators, embedded processors, GPU/NPU compute modules, and other units responsible for processing sensor data and executing control logic. These modules form the foundation of modern autonomous, humanoid, and perception-capable robots.
Component type encompassing System-on-Chip designs used as primary compute units in embedded devices, edge AI, and robotics applications.
Technical specification
Basic physical properties of NVIDIA Jetson T4000 — dimensions, weight and materials
Relations
Other hardware parts related to NVIDIA Jetson T4000
Production compute module (SoM) from the NVIDIA Jetson Thor family, built on the Blackwell architecture. Delivers up to 2070 TFLOPS (FP4) for robotics and physical AI, with 128 GB LPDDR5X.
NVIDIA flagship compute module for humanoids and physical AI - 2070 TFLOPS FP4, Blackwell GPU, 128 GB LPDDR5X.