Meta will fulfill its massive AI demands by co-developing multiple next-gen AI Silicon "XPUs" with Broadcom.
Meta & Broadcom Partner To Develop A Multi-Gigawatt AI Ecosystem Powered by Custom AI Silicon "XPUs"
Last month, Meta announced four AI chips featuring a custom design for its AI tasks. These XPUs (chips with multiple IPs) were branded under the MTIA AI lineup & each chip is optimized for a specific workload that spans GenAI inference, General-Purpose, and Training tasks. The four chips are listed below with their specs:
| Metric | MTIA 300 | MTIA 400 | MTIA 450 | MTIA 500 |
| Workload Focus | R&R Training | General | GenAI Inference | GenAI Inference |
| Module TDP | 800 W | 1200 W | 1400 W | 1700 W |
| HBM Bandwidth | 6.1 TB/s | 9.2 TB/s | 18.4 TB/s | 27.6 TB/s |
| HBM Capacity | 216 GB | 288 GB | 288 GB | 384-512 GB |
| MX4 Performance | — | 12 PFLOPs | 21 PFLOPs | 30 PFLOPs |
| FP8/MX8 Performance | 1.2 PFLOPs | 6 PFLOPs | 7 PFLOPs | 10 PFLOPs |
| BF16 Performance | 0.6 PFLOPs | 3 PFLOPs | 3.5 PFLOPs | 5 PFLOPs |
| Scale-up Domain Size | 16 | 72 | 72 | 72 |
| Scale-up Network (unidirectional bandwidth)* | 1 TB/s | 1.2 TB/s | 1.2 TB/s | 1.2 TB/s |
| Scale-out Network (unidirectional bandwidth)* | 200 GB/s** | 100 GB/s | 100 GB/s | 100 GB/s |
Now, Meta is officially announcing that it will further dive into custom MTIA chips, co-developed with Broadcom, to address its AI needs. Meta will work with Broadcom across chip design, advanced packaging, and networking, spanning multiple years and several custom XPU designs.
The first phase of this multi-Gigawatt partnership will aim to roll out an AI ecosystem that exceeds 1 Gigawatt. Meta has already highlighted that it plans to compete directly with other commercially available options and aims for a yearly multi-product cadence to meet its own demands.
Press Release: Today, Meta announced an expanded partnership with Broadcom to develop multi-generations of our next-generation MTIA (Meta Training and Inference Accelerator) chips. This custom silicon helps power AI across all of Meta's apps and services.
Broadcom will work with us across chip design, advanced packaging, and networking to help build out the massive computing foundation we need to deliver real-time AI experiences to billions of people. The partnership is built on Broadcom’s XPU platform, a technology designed for creating custom AI accelerators (XPUs), enabling optimization of Meta’s AI infrastructure across multiple silicon generations. Broadcom’s advanced Ethernet technologies will also enable seamless, high-bandwidth networking across Meta’s rapidly expanding AI compute clusters.
The agreement includes a commitment that exceeds 1GW, which is the first phase of a sustained, multi-gigawatt rollout, reinforcing a shared roadmap to co-design and scale the hardware required to bring personal superintelligence to billions of people globally.
"We are pleased to expand our strategic collaboration with Meta as they pioneer the next frontier of artificial intelligence,” said Hock Tan, President and CEO of Broadcom. “This initial MTIA deployment is just the beginning of a sustained, multi-generation roadmap to serve the trajectory of massive growth over the next few years that highlights Broadcom’s unmatched leadership in AI networking and the power of our foundational XPU custom accelerator platform.”
“Meta is partnering with Broadcom across chip design, packaging, and networking to build out the massive computing foundation we need to deliver personal superintelligence to billions of people,” said Meta founder and CEO Mark Zuckerberg. “As we roll out more than 1GW of our custom silicon to start and then multiple gigawatts over time, this partnership will give us greater performance and efficiency for everything we’re building.”
This expanded partnership with Broadcom and the continued evolution of MTIA are critical to Meta’s
broader AI infrastructure strategy, ensuring we have the custom compute foundation to deliver on our long-term AI ambitions at a global scale.
About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.
Follow Wccftech on Google to get more of our news coverage in your feeds.
