Broadcom Now Shipping World’s First 102.4 Tbps Switch in Production Volume
Rhea-AI Summary
Broadcom (NASDAQ: AVGO) announced that its Tomahawk 6 switch family is now shipping in production volume as of March 12, 2026. Tomahawk 6 reportedly doubles throughput versus Tomahawk 5 and supports 100G/200G SerDes with options for 512 200G or 1024 100G SerDes on a single chip.
The product targets scale-out and scale-up AI networks, enabling high-density XPU clusters (up to 128K XPU fabrics with two tiers and single-chip 512-XPU connectivity) and emphasizes lower latency, reduced optics complexity, and improved system power efficiency.
Positive
- Tomahawk 6 doubles throughput versus Tomahawk 5
- Production-volume shipment achieved in under three quarters from sampling
- 512 200G or 1024 100G SerDes option on a single chip
- Enables 128K-XPU two-tier AI fabrics and 512-XPU single-chip connectivity
- Supports 100G/200G SerDes for longer passive copper reach and lower optics
Negative
- None.
Key Figures
Market Reality Check
Peers on Argus
Peers showed mixed, mostly modest moves: TSM +0.18%, NVDA +0.05%, AMD -0.14%, QCOM -1.71%, MU +1.93%. No clear sector-wide reaction aligned with AVGO’s -0.29% pre-news move.
Historical Context
| Date | Event | Sentiment | Move | Catalyst |
|---|---|---|---|---|
| Mar 11 | AI optical DSP launch | Positive | -0.3% | Announced 3nm 400G/lane PAM-4 optical DSP for 1.6T–3.2T modules. |
| Mar 04 | Earnings and dividend | Positive | +4.8% | Reported record Q1 FY2026 results, dividend and $10B buyback authorization. |
| Mar 02 | Telco cloud platform | Positive | -0.2% | Launched VMware Telco Cloud Platform 9 targeting sovereign-ready telco infrastructure. |
| Feb 26 | AI compute SoC shipping | Positive | -3.2% | Began shipping 2nm 3.5D XDSiP compute SoC for AI clusters, initial Fujitsu use. |
| Feb 19 | 6G front-end SoC | Positive | +0.1% | Introduced BroadPeak BCM85021 6G digital front-end SoC with power reduction. |
Recent AI and product launches often saw negative or muted next-day moves, while earnings produced a positive reaction.
Over the past few weeks, Broadcom has issued several AI- and networking-focused announcements, including a 3.5D 2nm compute SoC, a 6G digital front-end SoC, and a 400G/lane optical DSP aimed at next‑generation AI networks. These technology updates around high-speed interconnects and AI infrastructure generally saw mixed to negative next‑day moves, while record Q1 FY2026 results on Mar 4 with strong AI-driven growth and capital returns produced a +4.8% reaction. Today’s Tomahawk 6 AI switch volume shipment fits this ongoing AI infrastructure build‑out narrative.
Market Pulse Summary
This announcement highlights Broadcom’s push deeper into AI networking, with the Tomahawk 6 family delivering a 102.4 Tbps switch and high-density 100G/200G SerDes aimed at very large XPU clusters. In context of recent AI compute, optical, and 6G product launches plus strong quarterly results, it reinforces a broad infrastructure roadmap. Investors may watch customer adoption, deployment scale in AI clusters, and how these platforms support future revenue and margin trends.
Key Terms
serdes technical
AI-generated analysis. Not financial advice.
Tomahawk 6 Family Switch Series Delivers Unmatched Performance for Scale-Out and Scale-Up AI Networks
PALO ALTO, Calif., March 12, 2026 (GLOBE NEWSWIRE) -- Broadcom Inc. (NASDAQ: AVGO), a global leader that designs, develops and supplies semiconductor and infrastructure software solutions, today announced that the Tomahawk® 6 family switch series is now shipping in production volume. Unprecedented for a chip of its scale, Tomahawk 6 moved rapidly from initial samples to production deployment.
“Broadcom’s ability to take Tomahawk 6 to production in less than three quarters from initial sampling is a testament to its innovation at scale,” said Asad Khamisy, senior vice president and general manager, Core Switching Group, Broadcom. “Tomahawk 6 doubles the throughput of its predecessor Tomahawk 5, representing a true breakthrough in AI infrastructure design. Our superior execution enables us to be the trusted technology partner for our customers’ demanding networking needs.”
Highly optimized for scale-out and scale-up AI networks used for training and inference, Tomahawk 6 provides advanced load balancing and congestion management for the highest network utilization and lowest job completion time. Tomahawk 6 delivers unmatched flexibility with support for 100G and 200G SerDes. It offers the industry’s most comprehensive set of AI routing features and interconnect options, designed to meet the demand of AI clusters with more than one million XPUs.
“With Tomahawk 6 now shipping, Broadcom is translating its roadmap into real-world deployment,” said Sameh Boujelbene, vice president and Analyst at Dell’ Oro Group. “The platform addresses the industry’s need for large-scale, low-latency fabrics with fewer switch tiers and reduced optical complexity. By supporting both scale-out and scale-up AI architectures at unprecedented density, Tomahawk 6 gives operators a practical path to build faster, more efficient XPU clusters.”
“Through relentless execution, Broadcom has been first to market generation after generation in data center switching,” said Bob Wheeler, Analyst at Large, LightCounting. “For AI scale-out networks, Tomahawk 6 enables a 128K-XPU network using only two switch tiers. Fewer tiers mean lower latency, simpler load balancing and congestion control, and fewer optics. For AI scale-up networks, a single Tomahawk 6 can connect 512 XPUs, providing single-hop all-to-all connectivity.”
The innovations of Tomahawk 6 extend far beyond the chip, delivering full system-level power efficiency and cost savings, enabled by Broadcom’s best-in-class SerDes and optics ecosystem. With industry leading SerDes, it provides the longest reach for passive copper interconnect, enabling high-efficiency, low-latency system design with the highest reliability and lowest total cost of ownership. The Tomahawk family includes a groundbreaking option for 512 200G or 1024 100G SerDes on a single chip, enabling customers to deploy AI clusters with extended copper reach and efficient use of XPUs and optics with native 100G/200G interfaces.
To learn more about the Broadcom Tomahawk 6 family click here. For more information on all Broadcom products please visit www.broadcom.com.
About Broadcom
Broadcom Inc. (NASDAQ: AVGO) is a technology leader that designs, develops, and supplies semiconductors and infrastructure software for global organizations’ complex, mission-critical needs. Broadcom combines long-term R&D investment with superb execution to deliver the best technology, at scale. Broadcom is a Delaware corporation headquartered in Palo Alto, CA. For more information, visit www.broadcom.com.
Broadcom, the pulse logo, Tomahawk, and Connecting Everything are among the trademarks of Broadcom. The term "Broadcom" refers to Broadcom Inc., and/or its subsidiaries. Other trademarks are the property of their respective owners.
Press Contact:
Jon Piazza
Corporate Communications
press.relations@broadcom.com
Telephone: +1 310 498 5254
FAQ
What does Broadcom say about Tomahawk 6 production timing (AVGO)?
How much faster is Tomahawk 6 compared to Tomahawk 5 (AVGO)?
What SerDes density options does Tomahawk 6 offer for AVGO customers?
How does Tomahawk 6 affect AI cluster scale for Broadcom (AVGO)?
What network architectures does Tomahawk 6 target for AVGO customers?
What system-level benefits does Broadcom cite for Tomahawk 6 (AVGO)?
