Meta's insatiable appetite for Nvidia AI chips could add up to $7 billion worth of H100 GPUs by the end of the year

Nvidia Hopper GPU die
(Image credit: Nvidia)

Remember when we reported some market data indicating Meta had snapped up 150,000 of Nvidia's beastly H100 AI chips? Now it turns out Meta wants to have more than double that at 350,000 of the big silicon things by the end of the year.

Most estimates put the price of an Nvidia H100 GPU at between $20,000 and $40,000. Meta along with Microsoft are Nvidia's two biggest customers for H100, so it's safe to assume it will be paying less than most.

However, some basic arithmetic around Nvidia's reported AI revenues and its unit shipments of H100 reveals that Meta can't be paying an awful lot if any less than the lower end of that price range, which works out to roughly $7 billion worth of Nvidia AI chips over two years. For sure, then, at the very least we're talking about many billion of dollars being spent by Meta on Nvidia silicon. 

Meta has also now revealed some details (via ComputerBase) about how the H100s are implemented. Apparently, they're built into 24,576-strong clusters used for training language models. At the lower end per-unit H100 price estimate, that works out at $480 million worth of H100s per cluster. Meta has provided insight into two slightly different versions of these clusters. 

To quote ComputerBase, one "relies on Remote Direct Memory Access (RDMA) over Converged Ethernet (RoCE) based on the Arista 7800, Wedge400 and Minipack2 OCP components, the other on Nvidia's Quantum-2 InfiniBand solution. Both clusters communicate via 400 Gbps fast interfaces."

In all candour, we couldn't tell our Arista 7800 arse from our Quantum-2 InfiniBand elbow. So, all that doesn't mean much to us beyond the realisation that there's a lot more in hardware terms to knocking together some AI training hardware than just buying a bunch of GPUs. Hooking them up would appear to be a major technical challenge, too.

But it's the 350,000 figure that is the real eye opener. Meta was estimated to have bought 150,000 H100s in 2023 and hitting that 350,000 target means upping that to fully 200,000 more of them this year.

Meta AI cluster

Meta's AI Cluster: Altogether now...the Arista 7800 bone's connected to the Quantum-2 InfiniBand bone! (Image credit: Meta)

According to the figures provided by research outfit Omnia late last year, Meta's only rival for sheer volume of H100 acquisition was Microsoft. Even Google was only thought to have bought 50,000 units in 2023. So it would have to ramp up its purchases by a truly spectacular amount to even come close to what Meta is buying.

For what it's worth, Omnia predicts that the overall market for these AI GPUs will be double the size in 2027 that it was in 2023. So, Meta buying a huge amount of H100s in 2023 and yet even more of them this year fits the available data well enough.

What this all means for the rest of us is anyone's guess. It's hard to predict everything from the impact this huge demand for AI GPUs will have on availability of humble graphics-rendering chips for PC gaming, let alone the details of how upcoming AI will advance over the next year or two.

Your next upgrade

Nvidia RTX 4070 and RTX 3080 Founders Edition graphics cards

(Image credit: Future)

Best CPU for gaming: The top chips from Intel and AMD.
Best gaming motherboard: The right boards.
Best graphics card: Your perfect pixel-pusher awaits.
Best SSD for gaming: Get into the game ahead of the rest.

As if these numbers weren't big enough, Omdia reckons Nvidia's revenues for these big data GPUs will actually be double in 2027 what it is today. They won't all be used for large language models and similar AI applications, but a lot of them will.

It's interesting that Omdia is so bullish about Nvidia's prospects in this market despite the fact that many of Nvidia's biggest customers in this market are actually planning on building their own AI chips. Indeed, Google and Amazon already do, which is probably why they don't buy as many Nvidia chips as Microsoft and Meta.

Strong competition is also expected to come from AMD's MI300 GPU and its successors, too, and there are newer startups including Tenstorrent, led by one of the most highly regarded chip architects on the planet, Jim Keller, trying to get in on the action.

One thing is for sure, however, all of these numbers do rather make the gaming graphics market look puny. We've created a monster, folks, and there's no going back.

TOPICS
Jeremy Laird
Hardware writer

Jeremy has been writing about technology and PCs since the 90nm Netburst era (Google it!) and enjoys nothing more than a serious dissertation on the finer points of monitor input lag and overshoot followed by a forensic examination of advanced lithography. Or maybe he just likes machines that go “ping!” He also has a thing for tennis and cars.

Read more
TAIPEI, TAIWAN - 2023/06/01: Jensen Huang, President of NVIDIA holding the Grace hopper superchip CPU used for generative AI at supermicro keynote presentation during the COMPUTEX 2023. The COMPUTEX 2023 runs from 30 May to 02 June 2023 and gathers over 1,000 exhibitors from 26 different countries with 3000 booths to display their latest products and to sign orders with foreign buyers.
Microsoft is Nvidia's biggest AI chip buyer of the year, and it's not even close. With ByteDance and Tencent coming out ahead of Zuck, Bezos, and Musk's outfits, too
SUQIAN, CHINA - JANUARY 27, 2025 - An illustration photo shows the logo of DeepSeek and ChatGPT in Suqian, Jiangsu province, China, January 27, 2025. (Photo credit should read CFOTO/Future Publishing via Getty Images)
China's DeepSeek chatbot reportedly gets much more done with fewer GPUs but Nvidia still thinks it's 'excellent' news
AMD Epyc 4th gen server processor on motherboard
AMD sees record revenue of $25.8 billion in 2024 thanks to data center growth—gaming last seen tumbling into a ditch
The NVIDIA stand at the Apsara Conference in Hangzhou, Zhejiang province, China, September 19, 2024. (Photo credit should read CFOTO/Future Publishing via Getty Images)
Nvidia share price plummets as it loses more than $600B in valuation, the biggest single-day loss in history
Microsoft Corporate Vice President, Windows and Devices Pavan Davuluri speaks about Recall during the Microsoft May 20 Briefing event at Microsoft in Redmond, Washington, on May 20, 2024. Microsoft unveiled a new category of PC on Monday that features generative artificial intelligence tools built directly into Windows, the company's world leading operating system. The tech giant estimates that more than 50 million "AI PCs" will be sold over the next 12 months, given the appetite for devices powered by ChatGPT-style technology. (Photo by Jason Redmond / AFP) (Photo by JASON REDMOND/AFP via Getty Images)
Microsoft plans on investing $80,000,000,000 in AI this year, with no sign of the machine learning spending spree stalling just yet
Images of Nvidia's Blackwell GPU from GTC.
OpenAI CEO Sam Altman says his company is 'out of GPUs' to which I reply 'welcome to the party, pal'
Latest in Graphics Cards
A side by side comparison of two Asus Q-Release systems, with the original design on the top and the bottom showing the apparently new design.
Asus appears to have quietly changed the design of its Q-Release PCIe slot after claims of potential GPU pin damage
A Colorful RTX 5080 and its box
Three lucky folks in India can win the dubious honour of buying an RTX 5080 GPU at Nvidia MSRP
Jensen Huang, co-founder and chief executive officer of Nvidia Corp., speaks while holding the company's new GeForce RTX 50 series graphics cards and a Thor Blackwell robotics processor during the 2025 CES event in Las Vegas, Nevada, US, on Monday, Jan. 6, 2025. Huang announced a raft of new chips, software and services, aiming to stay at the forefront of artificial intelligence computing. Photographer: Bridget Bennett/Bloomberg via Getty Images
Group allegedly trying to smuggle Nvidia Blackwell chips stare down bail set at over $1 million
Nvidia RTX 5090 Founders Edition graphics card on different backgrounds
AI will be crammed in more of the graphics pipeline as Nvidia and Microsoft are bringing AI shading to a DirectX preview next month
Nvidia RTX 50-series graphics cards alongside an RTX 4090
Nvidia says it's sold twice as many RTX 50-series cards as RTX 40-series in the first 5 weeks. I'd bloody well hope so given there was essentially just the RTX 4090 for competition
AMD Radeon RX 9070/9070 XT graphics cards with artistic renders of reference design cards circled
Looks like a reference design AMD RX 9070 XT card has shown up in China, but let's not get carried away with thoughts of MBA cards just yet
Latest in News
A woman with an arcane slingshot uses it to light a distant fire
Deconstructeam's next game is about training to shoot a single fireball at an impossible target
assassin's creed shadow naoe
We asked two parkour athletes to rate the realism of Assassin's Creed's acrobatics, and a surprising 'crime against parkour' might actually be one of the most realistic things they saw
Mechs fight on the outside of a spaceship
MechWarrior 5: Clans is getting DLC with playable Elementals and a fight on the outside of a spaceship
Aloy - Horizon
'I feel worried about this art form:' Unsurprisingly, the real Aloy from Horizon isn't a fan of AI Aloy
Crying laughing emoji with disturbing realistic elements for REPO
REPO's first update will add a new map and a 'duck bucket' so we can finally give that pesky quacker a time out
Man facing camera
The Day Before studio reportedly sues Russian website for calling infamous disaster-game a 'scam'