Broadcom custom accelerators
Co-designed XPUs behind most hyperscaler silicon.
Full Broadcom custom accelerators record →Head to head
Broadcom custom accelerators (Broadcom) and Intel Gaudi 3 (Intel) both sit in Chips & Compute. Intel Gaudi 3 shipped more tracked changes in the last 30 days (5 vs 0). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | Broadcom custom accelerators Broadcom | Intel Gaudi 3 Intel |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | 2025 | 1.24.1 |
| Entry cost | Enterprise supply agreements | Pricing not published. Available via Intel Tiber AI Cloud or OEM platforms. |
| Pricing tiers | — | OEM/cloud free |
| Model stack | powers Google TPU | Accelerator · Intel Gaudi 2 · Intel Gaudi 3 |
| Context window | — | n/a |
| Public API | ||
| Routes models | ||
| Changes / 30d | 0 | 5 |
| Origin | Global | Global |
| Capabilities | Custom XPU design, Tomahawk networking, Hyperscaler programs | 128GB HBM2e, Open Ethernet scale-out, PyTorch native, oneAPI toolchain, Price-performance focus, PyTorch Support, vLLM Integration, DeepSpeed Training |
Co-designed XPUs behind most hyperscaler silicon.
Full Broadcom custom accelerators record →Gaudi 3 targets price-performance against Nvidia parts with open Ethernet scale-out and an oneAPI/PyTorch software path.
Full Intel Gaudi 3 record →