Broadcom custom accelerators
Co-designed XPUs behind most hyperscaler silicon.
Full Broadcom custom accelerators record →Head to head
Broadcom custom accelerators vs Google TPU Ironwood
Broadcom custom accelerators (Broadcom) and Google TPU Ironwood (Google) both sit in Chips & Compute. Broadcom custom accelerators is the cheaper entry point at Enterprise supply agreements. Google TPU Ironwood shipped more tracked changes in the last 30 days (11 vs 0). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | Broadcom custom accelerators Broadcom | Google TPU Ironwood |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | 2025 | 7th-generation (Ironwood) |
| Entry cost | Enterprise supply agreements | from $5.4/unit |
| Pricing tiers | — | On Demand (us-central1) $12 · DWS Flex-start (us-central1) $6 · DWS Calendar Mode (us-central1) $8.4 · 1-year Commitment (us-central1) $8.4 · 3-year Commitment (us-central1) $5.4 · On Demand (europe-west2) $13.2 · DWS Flex-start (europe-west2) $6 · DWS Calendar Mode (europe-west2) $8.4 |
| Model stack | powers Google TPU | Gemini · Google TPU Ironwood · Ironwood · Ironwood (TPU v7) · Ironwood TPU · Ironwood TPU (7th Generation) · TPU v7 · TPU7x · TPU7x (Ironwood) · XLA compiler |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 0 | 11 |
| Origin | Global | Global |
| Capabilities | Custom XPU design, Tomahawk networking, Hyperscaler programs | 9,216-chip pods, inference optimised, liquid cooled, JAX + PyTorch/XLA, Large-scale training, Reasoning and inference, 9,216 liquid-cooled chips per pod, 42.5 ExaFlops performance |
Google TPU Ironwood
v7 TPU pods scaling to 9,216 chips, available through Google Cloud and used for Gemini.
Full Google TPU Ironwood record →