Tesla outlines SI6 and Dojo 3 chips in revised AI accelerator roadmap

Nov 6, 2026
Tesla's revised chip roadmap includes the SI6 inference accelerator and a redesigned Dojo 3 training chip that uses chiplets and stacked high bandwidth memory.

Tesla outlines a revised accelerator roadmap that includes its SI6 inference chip and Dojo 3 training chip, reports Tom's Hardware. The company is also replacing artificial intelligence branding with super intelligence and renaming its accelerators under SI labels.

Dojo 3, also called D3, will combine multiple chiplets, advanced packaging and stacked high bandwidth memory. The design differs from Dojo D1, which used wafer scale packaging and relied on on chip SRAM. Tesla has not disclosed D3's compute performance, memory capacity, manufacturing process or launch schedule.

The roadmap places SI6 in 2029 to 2030 and lists 80 times the compute performance and nine times the memory of SI4. SI4 is Tesla's current vehicle inference processor and the baseline for its Full Self Driving system, but the company does not publish its absolute compute performance.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

Guide
10 most valuable public AI chip companies

10 most valuable public AI chip companies

Publicly traded companies designing merchant silicon for AI computing, ranked by market capitalization at the close of 23 October 2026.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.