- The Qualcomm Dragonfly AI200 AI Accelerator Rack is the first of multiple releases planned by the chip designer in its bid to score victories in the data center segment.
- The upcoming Dragonfly AI250 accelerator leverages its proprietary High-Bandwidth Computing (HBC) system to deliver 18 times the theoretical bandwidth of its sibling.
- Qualcomm’s initiative comes in an increasingly lucrative data center market grappling with memory shortages.
It’s no secret that the modern AI server ecosystem is dominated by Nvidia in most countries, although China is increasingly turning to Huawei as a local provider of similar solutions.
Qualcomm may not be one of the first companies that come to mind when you think of AI data centers or the chips housed there, with many investors feeling like they’ve completely missed the boat in the server segment.
Qualcomm’s recent Investor Day 2026 event served as a reminder that it is not only still in the game, but also has ambitions to carve out a significant slice of an ever-growing pie by taking a different path than most of its HBM-operating competitors.
An alternative ecosystem to Nvidia’s industrial standards?
Much of Qualcomm’s Investor Day event focused on its plans to become a significant player in the AI data center market, which is currently dominated by OEMs deploying a combination of Nvidia and AMD accelerators alongside custom silicon (ASIC) offerings from Google, Meta, Microsoft and even Amazon’s AWS.
It aims to achieve this by differentiating itself from the competition, leveraging its own area of expertise to carve out an edge: efficient Low-Power Double Data Rate (LPDDR) memory stacked in a 3D array on top of its AI accelerators to drive the next generation of AI inference workloads.
Near-memory computing architecture isn’t exactly new in a market full of similar approaches, but the numbers are hard to argue with when it comes to Qualcomm’s offerings.
Qualcomm’s upcoming Dragonfly AI200 rack offers 43TB of LPDDR5X capacity and 414TB/s of memory bandwidth per rack, built from accelerator cards each carrying 768GB of LPDDR5X, making it an interesting offering, but hyperscalers will largely focus on its Dragonfly AI250 sibling which integrates high-bandwidth computing (HBC) under the hood.
Although it offers the same memory capacity per rack, its ability to leverage memory at up to 18 times the bandwidth of its sibling results in a theoretical maximum memory bandwidth of up to 7.4 PB/s per rack, a far cry from the AI200’s 0.4 PB/s.
The Dragonfly is positioned as an inference-focused accelerator for a reason; However, HBM is still better suited to certain tasks, such as model training rather than inference, making it the memory of choice for Nvidia’s upcoming Blackwell and Rubin GPUs, as well as AMD’s Instinct offerings.
That being said, Qualcomm’s solution is intriguing, although the numbers are for specific use cases and its ability to court hyperscaler giants such as Microsoft and Meta tends to indicate that it has a potential win, at least on paper, as AI data centers continue to focus increasingly on inference-centric solutions to deploy their increasingly complex models to a wider audience.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds.
