① NVIDIA announced that RTX Spark devices equipped with the N1X chip will begin shipping this October; ② At the same time, NVIDIA has launched the open-source tool NVIDIA PAIR, which can connect multiple RTX devices, DGX Spark systems, and even Apple devices on a home network, enabling the coordination of idle computing power to jointly process AI agent tasks.
NVIDIA announced that RTX Spark devices equipped with the N1X chip will begin shipping in October this year. The chip supports up to 128GB of unified memory and is equipped with a Blackwell GPU, offering ten billion floating-point operations per second. There are two versions of the N1X chip: the “full-capacity” version features 6140 CUDA cores and a 20-core Grace CPU, supporting 24GB to 128GB of unified memory; the other version has 5120 GPU cores and 18-core CPU, supporting only 24GB to 32GB of unified memory. Meanwhile, NVIDIA launched the open-source tool NVIDIA PAIR, which can connect multiple RTX devices, DGX Spark, and even Apple devices in a home network, scheduling idle computing power to collaboratively handle AI tasking. PAIR can automatically detect compatible devices in the same network, prioritizing use of idle resources to avoid affecting other tasks. For example, when users start playing games, PAIR can reduce or stop the use of the device’s computing power as needed. At the media briefing, NVIDIA product manager…