Qualcomm targets Nvidia, AMD, Huawei with Dragonfly AI accelerator rack loaded with 43TB of LPDDR5x, future generations set to smash 7PB/s bandwidth

TechRadarby Rahim AmirJune 30, 2026tech

Qualcomm's upcoming rack-scale inference platform, Dragonfly, comes with impressive numbers as it chooses to skip HBM for its more cost-effective and power-efficient proprietary HBC offerings.

This article was published on TechRadar (techradar.com). Read the full article on the original source:

Read full article on TechRadar

#Pro #hardware

Qualcomm targets Nvidia, AMD, Huawei with Dragonfly AI accelerator rack loaded with 43TB of LPDDR5x, future generations set to smash 7PB/s bandwidth

More from TechRadar

South Korean nuclear container ship proposal receives US approval for 15,000 TEU ultra-safe molten salt reactor design

I wanted great filter coffee and espresso without buying two appliances — and 9 months later, the Ninja Prestige DualBrew System is still my absolute favorite for both

Ukraine's heavy bomber drones airdrop ARK-1 mine-laying robots behind Russian lines

Hate the Copilot key in Windows 11? It looks like Microsoft's bringing in the option to remap it to do nothing — if you feel that's more useful

Nvidia reveals deep dive into what makes Vera CPU tick — with the super-powered Olympus core promising huge performance increases and more

Shokz' new OpenDots Air aren't flashy, but after a month of testing I can confidently say they're the best clip-style open earbuds for most people

GitHub restructures bug bounty program following flood of AI-generated reports

The Razer Kiyo V2 is an excellent webcam, even though its fancy new AI features aren't really that exciting