Tesla’s Next-Gen FSD Computer (HW5 / AI5) Rumored to Deliver 5x More Power

Tesla's current FSD computer (HW4/AI4)

Not a Tesla App

As Tesla pushes the boundaries of autonomous driving with each iterative FSD update, the hardware that powers every vehicle also needs to continue evolving. With FSD V13 already pushing the capabilities of today’s AI4 hardware, Tesla is actively looking to update its FSD hardware.

Korean news outlet MK (Korean) has provided what seems to be a credible glimpse into Tesla’s next hardware iteration, AI5, and what it could be capable of. MK’s report claims that Tesla is preparing for the production of its new AI5 FSD computer with a performance target of 2,000 to 2,500 TOPS (Trillion Operations Per Second). According to the report, Tesla is considering using Samsung and TSMC to manufacture the hardware.

Putting the Compute Power into Perspective

To grasp what exactly that 2,500 TOPS number means, let’s compare it to Nvidia’s recently released gaming GPUs, the RTX 5080 and the RTX 5090 (about $1,500 and $3,000 GPUs, respectively). The 5080 clocks in at 1,800 TOPS, while the 5090 pushes a powerful 3,400 TOPS. Those also come alongside power draws of 360 and 575 watts, respectively.

For a dedicated automotive AI chip to be able to place itself squarely in the middle of those performance numbers is quite a feat, especially given Tesla’s previous hardware. HW3 clocked in at a measly 144 TOPS, while HW4/AI4, the current generation, pulls in at around 500 TOPS, a solid 3- 5x leap over HW3.

During a past earnings call, Elon claimed AI5 could be as much as 10 times more capable than HW4, which would imply an astronomical 5,000 TOPS. The 2,000 to 2,500 TOPS figure from this new report, however, represents a 4- to 5-fold generational jump, which feels more grounded and aligned with recent performance improvements elsewhere.

What is a “TOPS”?

TOPS is essentially a raw measure of processing power for a specific type of math, one related to the math used by neural networks. For an AI like FSD, it's the single most important metric. Think of it like the AI’s IQ - more TOPS means the computer can think faster and process more information, letting it better understand the environment around the vehicle and make smarter decisions.

True Performance or Skewed?

The key to understanding Elon’s claims about the TOPS figures lies in specialization. Tesla’s FSD computer is what is known as an ASIC - an Application-Specific Integrated Circuit. Unlike a general-purpose GPU in a gaming PC, Tesla’s AI hardware is designed from the ground up for one singular purpose: running the specific types of neural networks that FSD relies on.

This focus allows for incredible efficiency and performance in its designated tasks, and Tesla likely measures performance internally against AI inference benchmarks built around FSD.

The rumor that Tesla is tapping both Samsung and TSMC is pretty significant here as well. Tesla has previously sourced its chips from Samsung but likely requires additional capacity from TSMC, the world’s largest chip fabricator. A multi-source structure like this means Tesla is already putting the pieces together to mitigate supply chain risks.

AI Powerhouse

The need for AI5’s immense power isn’t just about running the current version of FSD, but about being able to support future versions of FSD that may require more computing power. Tesla continues to increase the size of thei AI models, which means that they’ll require more memory. One of the challenges in autonomy is that decisions must be made in just fractions of a second so that the vehicle can react accordingly. If output wasn’t required in nearly real-time, the vehicle could analyze video frames for a longer period and come up with better output, but the need for output in a timely fashion makes computing power critical.

Tesla’s executive team has repeatedly mentioned that the path towards fully Unsupervised FSD and Robotaxi lies in massive computational power alongside redundancy. The system will need to run increasingly complex neural networks to handle edge cases with greater reliability and start the march of 9s (improving from 99% to 99.9% to 99.99%, and so on). Layers of redundancy and multiple checks during the decision-making process will also be required for safety, which also requires additional compute.

What About HW3 and AI4?

With all this talk of AI5, the immediate question for every current Tesla owner and short-term buyer is: “What about MY car?”

AI4 is currently Tesla’s gold standard, and what they’re building today’s FSD, including FSD Unsupervised, around. For now, it offers Tesla enough headroom to continue expanding the neural nets and pushing new builds, but eventually, it too will one day need an upgrade.

Tesla has already stated that AI5 and AI6 will progressively improve FSD and become safer, but that doesn’t mean previous vehicles will be upgraded. Vehicles will only be upgraded if they’re not able to run Unsupervised FSD at a rate that’s safer than humans. Newer models will always perform better and at higher safety levels, but that doesn’t mean older hardware won’t be capable of safe driving.

The real story here is HW3. While Tesla’s executives have previously said that Hardware 3 is “Robotaxi Ready,” the practical reality of FSD V12.6 and V13.2 has set in for many. With FSD V13 pushing the envelope today, and Tesla’s intent to upgrade HW3 vehicles if they can’t figure out a solution, it seems the end of the line is coming.

For owners of HW3 vehicles, this likely means Tesla is planning a retrofit based around AI5 - likely a lower-performance version that will fit the current HW3 power and cooling packages. There could be a similar solution in the future for AI4 vehicles if Tesla plans to address the other half of the fleet, but that’s likely years away and only if they’re not able to achieve autonomy on that hardware.

The neural nets required for FSD to drive itself without supervision in complex urban environments will be orders of magnitude more complex than what we see today in just a few years. AI5 isn't just an upgrade; it's the necessary hardware to advance FSD to the next level.

Follow

Follow

Follow

Tesla Autonomously Delivers Its First Vehicle to Customer — And It’s More Impressive Than Expected [VIDEO]

Not a Tesla App

In a world first, Tesla has successfully completed its first fully autonomous delivery of a new vehicle from Gigafactory Texas to a customer’s home. While Musk announced this was coming, some of the details make the achievement even more impressive.

The first fully autonomous delivery of a Tesla Model Y from factory to a customer home across town, including highways, was just completed a day ahead of schedule!!

Congratulations to the @Tesla_AI teams, both software & AI chip design!

— Elon Musk (@elonmusk) June 27, 2025

Traveling on the Highway

A Tesla Model Y left the factory, navigating highways at speeds up to 72mph, a day ahead of Tesla’s previously announced schedule. Most critically, Elon also confirmed two key factors that make this achievement even more impressive than Tesla’s launch of the Robotaxi last week.

There were no Safety Monitors in the car, and no remote operators took control of the Model Y at any time, really making this an amazing achievement.

While the launch of the Robotaxi was an amazing step for Tesla, this one easily takes the cake.

No Safety Monitor, No Passengers, No Limits

The significance of this event lies in just how it differs from the current Robotaxi service operating in Austin.

First and most importantly, there was no Safety Monitor. Nobody was sitting up front, ready to tap one of the emergency stop buttons on the screen. The vehicle was empty, fresh from the factory. This is the unsupervised experience and future that we’ve been waiting for.

Max speed was 72 mph -- Ashok Elluswamy

Why There Was No Safety Monitor

However, there is an important distinction with this autonomous ride — that there were no passengers. This is the crucial regulatory distinction. By operating as a logistics trip rather than as a commercial ride-hailing service, Tesla was likely able to bypass many of the stringent rules governing passenger transport. 

This freedom is what enabled the other key difference: operating with fewer restrictions. That included a 72mph top speed on the highway, which is well outside the geofenced Robotaxi Network that’s currently available in Austin.

Yup! Max speed was 72 mph 🏎️

— Ashok Elluswamy (@aelluswamy) June 27, 2025

Ahead of Schedule

This event wasn’t a surprise - Elon had previously stated that Tesla expects the first fully autonomous delivery to happen on June 28th. He even worked some flex time into that, saying the timing could potentially slip into early July.

It turns out that additional time wasn’t needed, as Tesla ended up delivering its first vehicle a day early. It seems that Tesla is pulling data quickly from its fleet of slightly modified Model Ys cruising the streets of Austin, which likely enabled the confidence behind giving this the green light.

Video of the Drive

Tesla shared a video of the entire drive, from the vehicle leaving Giga Texas to it arriving at the customer’s home. The entire ride took 30 minutes, crossing parking lots and going on the highway.

While there are some disadvantages to autonomous deliveries, they could lower the cost of a vehicle significantly.

World's first autonomous delivery of a car!

This Tesla drove itself from Gigafactory Texas to its new owner's home ~30min away — crossing parking lots, highways & the city to reach its new owner pic.twitter.com/WFSIaEU6Oq

— Tesla (@Tesla) June 28, 2025

Challenging Uber Eats and Others

This successful delivery is another fantastic use case for FSD that could be another entire business in and of itself for Tesla. The ability to autonomously move vehicles, potentially with cargo inside them, has massive implications for both Tesla’s factory-to-customer logistics, as well as challenging other services like Uber Eats and Skip the Dishes down the road.

Additionally, logistics-focused autonomy may be easier to scale than the Robotaxi network. It sidesteps many of the complex safety, liability, and customer-facing service challenges that come with carrying human passengers. This could be a faster and clearer path for regulatory approval.

Fork in the Road

But it's more than just a new business.

Back in 2022, Elon commissioned an art piece that now stands outside Giga Texas. It is, quite literally, A Fork in the Road. Part of Elon’s greater goal is to ensure we pass Fermi’s Great Filters, and that means ensuring we generate green energy, electrify and automate transportation, and move towards sustainable abundance.

Two years ago, I commissioned an art piece: A Fork in the Road.

Had to make sure that civilization took the path most likely to pass the Fermi Great Filters. pic.twitter.com/mYFzdAy6WF

— Elon Musk (@elonmusk) December 7, 2024

The point of the fork here is that Tesla’s first autonomous delivery isn’t just a publicity stunt. We’re finally here, at the fork in the road. We’ve hit it - true autonomous capabilities being demonstrated on public highways under a specific and challenging set of conditions. That’s a true Level 4 autonomous capability with no one in the car.

While Robotaxi is a fantastic step towards changing personal transport, this successful delivery proves that there are even more uses to FSD beyond what we’ve seen so far.

Follow

Follow

Follow

Tesla Issues Physical Recall for Some Model 3 & Model Y Vehicles Over Seat Fasteners

Not a Tesla App

Tesla has issued a new, voluntary safety recall for a small batch of Model 3 and Model Y vehicles due to an issue with improperly tightened fasteners in the first-row seats. 

The recall impacts only about 48 vehicles and will require a Tesla service visit to resolve. 

Improperly Tightened Fasteners

According to the recall notice, the issue stems from the first-row seating that may have been manufactured with improperly torqued fasteners that attach the seat back to the seat bottom. In some cases, the fasteners may be loose or missing, which could cause a rattle or the seat to detach.

This is a critical safety issue, as a seat back that is not properly anchored could detach, leaving the driver or passenger unsupported and increasing the risk of an accident.

According to Tesla’s investigation, this issue originated from a production change made for vehicles manufactured between April 3rd and May 7th of 2025. However, not all vehicles built within that date are impacted by the recall. The issue impacts 30 2026 Model Ys and 18 2025 Model 3s, across all variants, including RWD, AWD, and Performance (for the Model 3).

Thankfully, there have been no incidents related to this issue to date.

The Fix

Since this is a physical recall, Tesla will have to inspect impacted vehicles and replace and properly retorque the seat fasteners as needed, free of charge. 

Owners of vehicles who have been impacted have already been contacted under the voluntary recall, and most vehicles should have been repaired by the time this notice is formally issued.

You can also check if your VIN is impacted by a recall using Tesla’s Recall Tool.

Tesla has noted the repair should take approximately one hour of work at a Service Center, and up to two hours if a Mobile Ranger addresses the recall.

Follow

Follow

Follow