Tesla is already working on the silicon that will power its envisioned future of autonomy. Elon Musk took to X this week to share updates from an engineering review of the AI6 chip, revealing major expectations for the next-next-generation silicon platform.
Musk posted on X, "Tesla AI chip design engineering reviews are so great! Team is awesome. Our AI6 chip might set a record for most amount of usable intelligence from a wafer when factoring in yield."
Tesla is designing AI6 for a massive ecosystem, ranging from the Full Self-Driving software in commercial Robotaxis and consumer vehicles to Optimus humanoid robots, and even space-based data center applications. While AI6 is still in the engineering and design phase, the upcoming AI5 chip has already been “taped out” and is slated for mass production in late 2027. Given that Musk is targeting an aggressive nine-month development cycle for Tesla's future AI chips, we expect AI6 to hit production during the latter half of 2028.
Major Architectural Upgrades
The performance jumps are shaping up to be massive. The upcoming AI5 chip has already been touted as delivering 5 times the compute power of two AI4 chips, which is what current Tesla vehicles are powered by. Musk previously noted that AI6 will double the performance of AI5, representing not just a generational leap but a complete architectural shift in processing and memory management.
Starting with AI5, Tesla’s future hardware platforms will have much more memory, as the latest FSD models have been capping out the available memory on AI4.
To prevent processing bottlenecks, both AI6 and the mid-cycle AI6.5 refresh Musk teased earlier this spring will dedicate roughly half of their TRIP AI computation accelerators to SRAM. This ultra-fast onboard memory lets the processor run complex AI calculations in a high-speed workspace without waiting on main system memory. For the main system memory itself, the AI6 design moves to faster LPDDR6 memory, a step up from the LPDDR5 or LPDDR5X configurations expected on the next-gen AI5 chip architecture.
Production and Integration Plans
Manufacturing plans are already falling into place. Tesla is closely collaborating with Samsung, which will manufacture AI6 in Texas at its new semiconductor facility. Beyond that $16.5 billion chip manufacturing deal, Tesla has also partnered with Intel and SpaceX for the TERAFAB AI chip project to vertically integrate semiconductor production.
Owners should not expect this new silicon in cars immediately. Musk has specified that Tesla's next-gen AI chips are not coming to vehicles first, choosing to instead deploy them into Optimus robots and the supercomputer clusters that train Tesla’s neural networks before scaling down to consumer cars. Musk already considers current AI4 setups powerful enough to beat human driving safety, giving the hardware team plenty of time to refine AI6 before it hits public roads.
