Tesla Dojo D1
Tesla's in-house training chip for the Dojo supercomputer: 50 billion transistors on a 645 mm² die, made by TSMC at 7 nm, in production from July 2023. Tesla shut Dojo down in August 2025 to focus on AI6. Sources and verification dates.
NodeTSMC 7 nm
Every published figure
Source per value- Owner The company that specified the chip and runs it in its own cloud, data centers or products.
- Tesla 1
- Role What the owner says the chip is for: training, inference, both, or a general-purpose server CPU.
- Training 1
- Foundry The fab that manufactures the die (TSMC, Samsung, SMIC, Intel).
- TSMC 1
- Node Process node as the owner or foundry states it, for example 'TSMC N3' or '7 nm'.
- TSMC 7 nm 1
- Status Announced: public roadmap without verified deployment. Sampling: first silicon or limited internal use. Preview: customers can request early access, without a GA claim. Deployed: stated production use or general availability. Discontinued: program stopped.
- Discontinued 2
- Announced Year the owner first announced the chip publicly.
- 2,021 1
- Deployment scale The largest deployment the owner or a named report states: chip counts, clusters, gigawatts or regions.
- Tesla targeted 100 exaflops of total compute by October 2024, roughly 276,000 D1 chips; it never confirmed reaching it. 1
- How to get it How an outside buyer can use the chip: a named cloud instance or service, a product, or 'Internal only'.
- Internal only 1
Not verified in the sources reviewed: design partner, partner basis, memory, memory capacity, memory bandwidth, bf16, fp16, mxfp8, mxfp4, mx8, mx4, fp8, int8, fp4, precision note, power, largest pod.
Sources
- TechCrunch: Tesla Dojo, Elon Musk's big plan to build an AI supercomputer, explained accessed 2026-11-11
- TechCrunch: Tesla shuts down Dojo accessed 2026-11-11