Qualcomm
CPUServerReleased —

Qualcomm Dragonfly C1000

The Qualcomm Dragonfly C1000 is Qualcomm's first-generation data center CPU, unveiled in June 2026 at its Investor Day as part of the new Dragonfly data center portfolio. It is a multi-chiplet design with more than 250 custom Oryon cores, aimed at AI head nodes as well as general-purpose and agentic AI workloads, with support for CXL and PCI Express Gen 7. Meta has agreed to deploy it in its server fleet under a multi-generation agreement, and Qualcomm plans to begin production in the second half of 2028.

General

Manufacturer
Qualcomm
Model
Qualcomm Dragonfly C1000
Segment
Server
Generation
Dragonfly (1st Gen)
Codename
—
Architecture
ARM64
Microarchitecture
Qualcomm Oryon
Release date
—

Cores & clocks

Cores / threads
—
Base clock
—
Boost clock
—
TDP (design W)
—
Unlocked
✕ No
L2 cache
—
L3 cache
—
Technology (nm)
—

Platform

Socket
—
2-CPU (multi-socket)
✕ No
Integrated GPU
None
Memory type
—
Memory size
—
ECC memory
—
PCIe
PCIe 7.0

Instructions & AI

Instruction extensions
—
NPU
None

OS support

Notes
Operating system support has not been announced for this unreleased data center processor. macOS is not supported.
All Qualcomm CPUs →

Server cpus from Qualcomm announced around the same time as the Qualcomm Dragonfly C1000. Add any of them to your compare list to see the specs side by side.