Google TPU Ironwood
v7 TPU pods scaling to 9,216 chips, available through Google Cloud and used for Gemini.
Full Google TPU Ironwood record →Head to head
Google TPU Ironwood vs Cerebras WSE-3
Google TPU Ironwood (Google) and Cerebras WSE-3 (Cerebras) both sit in Chips & Compute. Google TPU Ironwood is the cheaper entry point at from $5.4/unit. Google TPU Ironwood shipped more tracked changes in the last 30 days (16 vs 10). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | Google TPU Ironwood | Cerebras WSE-3 Cerebras |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | Ironwood (7th generation) | WSE-3 |
| Entry cost | from $5.4/unit | Free tier · from $10/unit |
| Pricing tiers | On Demand (us-central1) $12 · 1-year Commitment (us-central1) $8.4 · 3-year Commitment (us-central1) $5.4 · DWS Flex-start (us-central1) $6 · DWS Calendar Mode (us-central1) $8.4 · On Demand (europe-west2) $13.2 · 1-year Commitment (europe-west2) $9.24 · 3-year Commitment (europe-west2) $5.94 | Free Trial free · Developer $10 · Enterprise free |
| Model stack | Gemini · Ironwood · Ironwood (TPU v7) · Ironwood TPU · Ironwood TPU (7th Generation) · TPU v7 · TPU7x · TPU7x (Ironwood) · XLA compiler | Codex-Spark · Gemma · Gemma-4-31B · GLM-4.7 · GPT 5.6 Sol · GPT-5.6-Sol-Ultrafast · Kimi K2.6 · Llama · Llama / Qwen / GPT-OSS · Qwen · WSE-3 |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 16 | 10 |
| Origin | Global | Global |
| Capabilities | 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 | wafer-scale engine, record token/s on open models, CS-3 systems, training clusters, Wafer-scale AI inference, Cerebras PyTorch, ModelZoo, Low-level SDK |
Cerebras WSE-3
Single-wafer accelerators delivering the fastest published open-model token rates.
Full Cerebras WSE-3 record →