Qualcomm launches Cloud AI 100 Ultra AI accelerator card
Original title: Qualcomm Cloud AI 100 Ultra – 150W AI Accelerator Card with 128GB at 548GB/s
Qualcomm Cloud AI 100 Ultra offers 150W TDP, 128GB DRAM and 548GB/s bandwidth for cloud and on-premises AI inference.
Qualcomm released the Cloud AI 100 Ultra, its newest AI inference card. It supports Generative AI and large language models with up to 576MB SRAM and 64 AI cores. The card delivers peak performance of 870 TOPS integer and 288 TFLOPS floating point operations. It includes PCIe Gen4 16-lane interface and is part of the Qualcomm AI Inference Suite with OpenAI-compatible APIs.
- 150W TDP for cloud and on-prem deployment
- 128GB LPR4x DRAM at 548GB/s bandwidth
- 576MB on-die SRAM with 64 AI cores
- Supports computer vision, NLP and transformer LLMs
- Vendors
- Qualcomm
- Products
- Cloud AI 100 Ultra
From the original article
5 min read at qualcomm.comOverviewQualcomm® AI Inference Suite for Cloud and On-PremVideoSpecifications Delivers the performance and power efficiency necessary to deploy and accelerate AI inference at-scale The Qualcomm Cloud AI 100 Ultra, the newest member of our portfolio of cloud artificial intelligence (AI) inference cards, is a performance- and cost-optimized AI inference solution, designed for Generative AI and large language models…
By peter_d_sherman · qualcomm.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.