Monday, January 6th 2025
NVIDIA Puts Grace Blackwell on Every Desk and at Every AI Developer's Fingertips
NVIDIA today unveiled NVIDIA Project DIGITS, a personal AI supercomputer that provides AI researchers, data scientists and students worldwide with access to the power of the NVIDIA Grace Blackwell platform. Project DIGITS features the new NVIDIA GB10 Grace Blackwell Superchip, offering a petaflop of AI computing performance for prototyping, fine-tuning and running large AI models.
With Project DIGITS, users can develop and run inference on models using their own desktop system, then seamlessly deploy the models on accelerated cloud or data center infrastructure. "AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers," said Jensen Huang, founder and CEO of NVIDIA. "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."
GB10 Superchip Provides a Petaflop of Power-Efficient AI Performance
The GB10 Superchip is a system-on-a-chip (SoC) based on the NVIDIA Grace Blackwell architecture and delivers up to 1 petaflop of AI performance at FP4 precision.
GB10 features an NVIDIA Blackwell GPU with latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink -C2C chip-to-chip interconnect to a high-performance NVIDIA Grace CPU, which includes 20 power-efficient cores built with the Arm architecture. MediaTek, a market leader in Arm-based SoC designs, collaborated on the design of GB10, contributing to its best-in-class power efficiency, performance and connectivity.
The GB10 Superchip enables Project DIGITS to deliver powerful performance using only a standard electrical outlet. Each Project DIGITS features 128 GB of unified, coherent memory and up to 4 TB of NVMe storage. With the supercomputer, developers can run up to 200-billion-parameter large language models to supercharge AI innovation. In addition, using NVIDIA ConnectX networking, two Project DIGITS AI supercomputers can be linked to run up to 405-billion-parameter models.
Grace Blackwell AI Supercomputing Within Reach
With the Grace Blackwell architecture, enterprises and researchers can prototype, fine-tune and test models on local Project DIGITS systems running Linux-based NVIDIA DGX OS, and then deploy them seamlessly on NVIDIA DGX Cloud, accelerated cloud instances or data center infrastructure.
This allows developers to prototype AI on Project DIGITS and then scale on cloud or data center infrastructure, using the same Grace Blackwell architecture and the NVIDIA AI Enterprise software platform.
Project DIGITS users can access an extensive library of NVIDIA AI software for experimentation and prototyping, including software development kits, orchestration tools, frameworks and models available in the NVIDIA NGC catalog and on the NVIDIA Developer portal. Developers can fine-tune models with the NVIDIA NeMo framework, accelerate data science with NVIDIA RAPIDS libraries and run common frameworks such as PyTorch, Python and Jupyter notebooks.
To build agentic AI applications, users can also harness NVIDIA Blueprints and NVIDIA NIM microservices, which are available for research, development and testing via the NVIDIA Developer Program. When AI applications are ready to move from experimentation to production environments, the NVIDIA AI Enterprise license provides enterprise-grade security, support and product releases of NVIDIA AI software.
Availability
Project DIGITS will be available in May from NVIDIA and top partners, starting at $3,000. Sign up for notifications today.
With Project DIGITS, users can develop and run inference on models using their own desktop system, then seamlessly deploy the models on accelerated cloud or data center infrastructure. "AI will be mainstream in every application for every industry. With Project DIGITS, the Grace Blackwell Superchip comes to millions of developers," said Jensen Huang, founder and CEO of NVIDIA. "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."
The GB10 Superchip is a system-on-a-chip (SoC) based on the NVIDIA Grace Blackwell architecture and delivers up to 1 petaflop of AI performance at FP4 precision.
GB10 features an NVIDIA Blackwell GPU with latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink -C2C chip-to-chip interconnect to a high-performance NVIDIA Grace CPU, which includes 20 power-efficient cores built with the Arm architecture. MediaTek, a market leader in Arm-based SoC designs, collaborated on the design of GB10, contributing to its best-in-class power efficiency, performance and connectivity.
The GB10 Superchip enables Project DIGITS to deliver powerful performance using only a standard electrical outlet. Each Project DIGITS features 128 GB of unified, coherent memory and up to 4 TB of NVMe storage. With the supercomputer, developers can run up to 200-billion-parameter large language models to supercharge AI innovation. In addition, using NVIDIA ConnectX networking, two Project DIGITS AI supercomputers can be linked to run up to 405-billion-parameter models.
Grace Blackwell AI Supercomputing Within Reach
With the Grace Blackwell architecture, enterprises and researchers can prototype, fine-tune and test models on local Project DIGITS systems running Linux-based NVIDIA DGX OS, and then deploy them seamlessly on NVIDIA DGX Cloud, accelerated cloud instances or data center infrastructure.
This allows developers to prototype AI on Project DIGITS and then scale on cloud or data center infrastructure, using the same Grace Blackwell architecture and the NVIDIA AI Enterprise software platform.
Project DIGITS users can access an extensive library of NVIDIA AI software for experimentation and prototyping, including software development kits, orchestration tools, frameworks and models available in the NVIDIA NGC catalog and on the NVIDIA Developer portal. Developers can fine-tune models with the NVIDIA NeMo framework, accelerate data science with NVIDIA RAPIDS libraries and run common frameworks such as PyTorch, Python and Jupyter notebooks.
To build agentic AI applications, users can also harness NVIDIA Blueprints and NVIDIA NIM microservices, which are available for research, development and testing via the NVIDIA Developer Program. When AI applications are ready to move from experimentation to production environments, the NVIDIA AI Enterprise license provides enterprise-grade security, support and product releases of NVIDIA AI software.
Availability
Project DIGITS will be available in May from NVIDIA and top partners, starting at $3,000. Sign up for notifications today.
13 Comments on NVIDIA Puts Grace Blackwell on Every Desk and at Every AI Developer's Fingertips
Something like a RTX 5070 + 16 ARM cores would be pretty killer. But probably too low margin for Nvidia to market, maybe they'll let MediaTek do it.
Nvidia can make Mediatek look like the hi end brand in the ARM ecosystem.
www.dfrobot.com/kit-004.html?tracking=LATTEPANDAMU
Still a reasonable price given that it's cheaper than an apple equivalent.The product at hand has a Grace CPU, not a mediatek one. They helped with the SoC design and likely fabbing, but it's still a neoverse CPU under the hood.A GB205-like chip with a bigger memory bus and unified LPDDR5X memory wouldn't be bad at all, it'd be similar to Strix Halo even.
Instslling a regular GPU in an x86 SBCs kills all the fun of it, and lacks the unified memory.
I'm of the opinion that for a good craftsman, a good tool is always worth the price, it might cost more up front but if you can recover the costs by creating better, or more products as a result, why not.
I can rent a GH200 with 96GB of vram and 480GB of RAM with C2C for $1.5/hour. That Digits won't be anywhere close in performance nor that useful to me to justify that price. Same reason as I haven't upgraded my 3090s.
At $2k I'd be more willing to grab one just because it's a fun device that I'd like to tinker with, so it'd be more of a hobby excuse than actual utility.
It's doubtful that nVidia feels motivated to grab more consumer market share these days, seeing as they already own 90% of it where they compete and it is barely worth 1/30th of their enterprise division. And you know they're closely watching Qualcomm struggle with its own x86 competitor ambitions.
Genius idea.
I don't think it's worth it to let go of over $5k grand compared to the cost x benefit of a gh200 (that still has more vram).