Observed Signal · Sep 7, 2026 · Technical Release · Source: SemiAnalysis · Impact: 5/5 · Sentiment: Positive
Google TPUv7 Ironwood Delivers Up to 50% Better Performance per Dollar
SemiAnalysis, an independent analyst firm, published third-party inference benchmarks for Google's TPUv7 Ironwood, comparing it against NVIDIA's B200 and B300 GPUs. The results show Ironwood delivering up to 50% better performance per dollar in apples-to-apples comparisons, with a 19-34% lower cost per token at typical interactivity levels. Key factors include Google's co-designed hardware and software stack, the emerging TorchTPU external stack providing native PyTorch support, and optimizations across kernels and serving engines (vLLM, SGLang). Google is externalizing its TPU infrastructure, selling chips outright and on Google Cloud, with Anthropic as a major customer. The TorchTPU stack is in private beta, open-sourcing around mid-October, and future work includes speculative decoding, disaggregated serving, and KV-cache offloading, positioning TPUs as a strong competitor in the AI inference market.
Major technical release from Google showing TPUv7 Ironwood outperforming NVIDIA GPUs on performance per dollar, with significant implications for AI inference cost structure and the competitive landscape.
Track Google Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Google's TPUv7 Ironwood delivers up to 50% better performance per dollar compared to NVIDIA B200/B300 GPUs.
- Ironwood costs approximately $0.181 per million tokens at 100 tokens/s/user, vs $0.222 for B200 and $0.276 for B300.
- Anthropic has committed to over one million TPUs, including 400k+ direct purchases and 600k+ rented via GCP.
- The TorchTPU stack, enabling native PyTorch on TPUs, is in private beta and will be open-sourced around mid-October.
- TPUv8i Boardfly, with native FP4 support, is expected to be competitive with NVIDIA's Rubin NVL72.
Connected Companies & Entities
“Google has been running disaggregated serving internally and is externalizing its TPU stack.”
“Ironwood delivers up to 50% better performance per dollar compared to B200/B300 from NVIDIA.”
“SemiAnalysis published third-party inference results for TPUv7 Ironwood on InferenceX.”
“Anthropic is the biggest user of TPUs, surpassing Deepmind's own use by 2029.”
“vLLM and SGLang are the two major open-source production inference serving stacks, and TorchTPU will be the go-to backend for them going for...”
“Red Hat is investing heavily in collaboration with Google to make the TorchTPU backend a first-class experience.”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Google TPUv7 Challenges NVIDIA on AI Inference
SemiAnalysis released first official long-context, multi-turn agentic inference benchmarks (InferenceX/AgentX) showing Google's TPUv7 (Ironwood) delivers competitive or superior performance per dollar versus NVIDIA GPUs on several large models including GLM-5.2, Qwen3.5, Kimi K3, and Meta's Muse Spark Open. On GLM-5.2 FP8, TPUv7 delivers 1.2x-2.7x tokens per dollar of B200/B300/MI355X; on Qwen3.5 with llm-d disaggregated serving, TPUv7 beats GB300 FP8; on Kimi K3, TPUv7 delivers 1.15x-2.5x tokens per dollar of GB200/B200/B300/MI355X. NVIDIA's counter-submission on GB300 FP4 is still 1.64x worse per dollar than TPUv7 FP8 on Qwen3.5. The article highlights TPU's growing ecosystem adoption (Oracle, OpenAI, Anthropic, Meta) and contrasts NVIDIA's bureaucracy with AMD's agility in open-source collaboration. TPUv7 lacks native FP4 support until TPUv8 (Q1 2027), but competitive FP8 performance positions TPU as a serious alternative in AI inference.
Google open-sources TorchTPU to rival Nvidia's AI chip dominance
Google has open-sourced TorchTPU, its version of the PyTorch AI framework, enabling developers to run PyTorch apps on Google's TPUs with minimal changes. This move follows Amazon's similar release of TorchNeuron, aimed at porting apps to its Trainium chips. Both companies seek to break Nvidia's stronghold on AI hardware, where most AI apps are optimized for Nvidia GPUs. Google has collaborated with Meta, Hugging Face, and other tool makers to ensure compatibility. The company also launched a TPU agent suite to assist developers in migrating apps. This is part of a broader trend to increase competition in the AI infrastructure market.
Google's TPU Fleet Dominates AI Compute Growth
An analysis by Gennaro Cuofano highlights a major structural shift in AI infrastructure: Google’s TPU fleet expanded 11.5× over seven quarters, with quarterly additions accelerating. The report states Google's TPU power draw now exceeds Microsoft’s entire AI compute stack, and that by Q4 2025 Google added more compute in a single quarter than xAI had built in total. These data points indicate a widening infrastructure lead for Google that could cascade into lower per‑token costs, faster model iteration, and a larger operational moat for products and services that depend on large-scale inference and training capacity. The piece frames the compute growth as a pivotal industry trend with broad implications for competition, capability, and deployment timelines across AI-dependent sectors.
Receive all future signals for Google & competitors in your briefing
Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.
