It’s official, NVIDIA’s Project Digits is now the world’s smallest AI supercomputer capable of running 200-billion-parameter large language models, thanks to the GB10 Grace Blackwell Superchip. The latter offers a petaflop of AI computing performance for prototyping, fine-tuning as well as running large AI models.
Technically speaking, NVIDIA’s GB10 Superchip is a system-on-a-chip (SoC), based on the NVIDIA Grace Blackwell architecture, that delivers up to 1 petaflop of AI performance at FP4 precision. Featuring an NVIDIA Blackwell GPU with the latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink-C2C chip-to-chip interconnect to a high-performance NVIDIA Grace CPU. Even more impressive is the fact that two Project DIGITS AI supercomputers can be linked to run up to 405-billion-parameter models. Available in May, priced from $3,000 USD.
- 【NEW GENERATION CPU-N95】--Newest 12th Intel Alder Lake N95 (1.7GHz, MAX TO 3.4GHz, 4x cores, 6MB L3 Cache) processor (2025 New Releases). Compared...
- 【16GB RAM 512GB SSD UP TO 2TB】--KAMRUI mini pc with high-speed 16GB DDR4, Built-in 512GB M.2 2280 SSD.16GB of RAM memory makes your entire system...
- 【SMALL BUT POWERFUL PC】--MINI PC Silver Series has a great texture. The mini computer measures only 5.1 in * 5.1 in * 1.96 in, you can be easily...
AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers. Placing an AI supercomputer on the desks of every data scientist, AI researcher and student empowers them to engage and shape the age of AI,” said Jensen Huang, founder and CEO of NVIDIA.
