NVIDIA Begins Sampling Its Next-Gen AI Powerhouse, Blackwell, All Over The World, Mass Production On-Track

Muhammad Zuhair
NVIDIA To Ship Out 150K-200K Blackwell GB200 AI Servers In Q4 2024 Alone, Microsoft Being The Leading Buyer 1

NVIDIA will begin sampling the first Blackwell AI accelerators across the globe this week as the firm demonstrates unparalleled performance with its next-gen architecture.

NVIDIA CEO Jensen Huang Provides Update On Blackwell At The SIGGRAPH, Sampling Starts This Week, Also Reveals Several New "AI Bits"

It was a delight to see NVIDIA's CEO Jensen Huang on the stage during the SIGGRAPH 2024, where Team Green showed how the AI hype will lead to the transformation of the business industry.

Related Story NVIDIA Blackwell Sweeps Every MLPerf 6.0 Benchmark With No Competition In Sight, While GB300 Systems Run Up to 60% Faster Than GB200

Since SIGGRAPH is more focused on the "software side of things," NVIDIA didn't go much into the progress of its AI products; however, it did give us a glimpse of what's happening with the Blackwell architecture, stating that the firm expects engineering samples to be sent to customers all over the world by this week, showing that the debut of the products is closer than ever.

NVIDIA's Blackwell AI products are set to be the most "successful" ones in the firm's history since the firm has already bagged massive demand in the pre-release period, with the likes of Meta, Microsoft, and Google rushing towards the AI giant in order to reserve their slots.

The supply chain is already gearing up for yet again another "gold rush", with partners such as TSMC and SK hynix upscaling their production facilities massively. So, it's safe to say that NVIDIA & Blackwell will yet again replicate the same financial results as brought in by Hopper products, but probably two to five times, maybe even greater.

Apart from Blackwell, NVIDIA also announced progress in its "AI factory" ecosystem, with the addition of features expected to increase generative AI capabilities in NVIDIA's NIM inference microservices. Through this, the firm expects the adoption of AI into industrial workloads, ultimately expanding the influence of the technology to new domains, further fueling the progress.

Last but not least, we saw NVIDIA's CEO Jensen Huang and Meta's CEO Mark Zuckerberg on the stage together. Both personalities discussed the ongoing endeavors in the AI industry, especially the integration of AI into every form of business. Apart from that, Meta's CEO revealed that they have managed to add 600,000 of NVIDIA's H100s for their AI computing power, which showed how deep of a collaboration both firms are currently involved in.

The highlight of the event was when both CEOs exchanged their leather jackets, with Huang wearing something different in public for the first time, although for a very short moment.

Muhammad Zuhair Photo

About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.

Follow Wccftech on Google to get more of our news coverage in your feeds.

Button