2 Sources
[1]
Xiaomi Unveils Custom Chip For Driver-Assist Features
* Xiaomi has unveiled its first in-house chips dedicated to AI and self-driving. * The automaker currently relies on Nvidia for its hardware, though that could change as early as next year. * This makes Xiaomi the latest Chinese automaker to ditch U.S.-sourced chips in favor of self-produced silicon. Xiaomi's next move in cars is happening somewhere you'll never see it: buried deep inside the dashboard, under a heatsink, doing the ungodly amount of math required advanced driver-assistance features. On Monday, Xiaomi unveiled a family of in-house silicon, including the Xring D100 chip designed for "intelligent driving." This makes Xiaomi the latest EV maker investing in home-grown AI inference rather than relying on a market cornered by Nvidia. Xiaomi's SU7 and YU7 EVs have historically relied on Nvidia's hardware, beginning with the older Drive Orin system and now the Drive Thor. That decision locked the Chinese brand in with the American GPU producer at a time when the entire world is looking at the same company for chips to power the insatiable appetite for AI. Designing chips in-house comes with a few potential upsides. The D100 could be a buffer against soaring AI chip costs. It means Xiaomi gets to tune its hardware to its own sensor, software, and driving models. It also means that Xiaomi gets more control over cost, supply, and development timing. Other Chinese automakers like BYD, Nio, Xpeng have begun exploring in-house silicon development too. This is extremely important as key players in the U.S. AI arms race, like Anthropic's Dario Amodei, call for stricter export control of AI compute. Here in the States, Rivian recently announced a custom chip for advanced driving features that is debuting in the R2. Tesla has been designing its own chips to run Full Self-Driving (Supervised) for years. Let's nerd out on the Xiaomi silicon's specs for a moment. The D100 packs a 20-core CPU and a 16-core NPU. Xiaomi says that this is the first chip build in mainland China on a 3-nanometer chip production process (meaning it can potentially offer more efficiency and processing density in a single chip). It also supports up to 160 gigabytes of unified memory -- enough to run up to a 200-billion-parameter model directly on the device. For comparison, Nvidia's current Thor hardware is offered with a 14-core, 4-nanometer processor and up to 128GB of memory. Tesla's current Hardware 4 offers 16GB of memory on a single chip and is built on a 7nm process. Its upcoming Hardware 5 is targeting an even more efficient 2nm manufacturing process and is expected to feature up to 144GB of memory. It's important to point out that it is possible for a system to offer more compute capacity but have lower overall performance due to optimization of overall efficiency. It's not clear if that's the case with Xiaomi's hardware compared to Nvidia or, say, Tesla, because Xiaomi has yet to reveal the system's actual Trillions of Operations Per Second (TOPS), which is a key measurement of speed and performance in AI inference. Xiaomi says that it's poured more than $3 billion into the development of its new hardware. That might seem like an expensive way to avoid buying another company's chips, but Xiaomi's top brass clearly believe the independence outweighs the R&D costs. That figure includes the Xring D100, as well as its O100 AI acceleration chip and O3 System-on-Chip (SoC) platform meant for mobile devices. The O3 is slated to debut in Xiaomi's upcoming 18 Fold cell phone, and the D100 and O100 are planned for commercial applications starting next year.
[2]
Xiaomi's New Chip Strategy Could Change its Smartphone Business
Xiaomi unveiled three new in-house chips for smartphones, AI devices and cars. The move could help the company rely less on outside chip makers. Xiaomi is taking a bigger step into chipmaking. The company introduced three new chips called Xring O3, Xring O100, and Xring D100. The first chip to reach buyers will be Xring 03, a 3nm processor that will power the Xiaomi 18 Fold and the Pad 9 Pro Max. Notably, both these devices will launch in China this September. The chip reportedly has a 10-core all-big-core CPU with a 16-core G2-Ultra NX GPU. Additionally, the chip contains a 60% gain in CPU performance, 85% better graphics, and 64% improved efficiency. Most importantly, it is the first Xiaomi chip to support LPDDR6, which is rated at 113.8 GB/s. The next one that users will access seems to be the Xring O100, a 6nm AI accelerator. This chip will deliver 1.22 TB/s of near-memory bandwidth, designed for on-device AI in phones, cars, and robots. The move shows that Xiaomi wants more control over the key parts inside its products. Xring D100 is built for intelligent driving. The chip has a 20-core CPU, support for 160GB of unified memory, and the ability to run 200-billion-parameter models locally. However, this chip is scheduled to be launched officially in 2027.
Share
Copy Link
Xiaomi unveiled three in-house chips—Xring O3, O100, and D100—designed for smartphones, AI devices, and intelligent driving. The move represents a $3 billion investment to reduce dependence on external suppliers like Nvidia and marks Xiaomi as the latest Chinese automaker pursuing custom silicon for advanced driver-assistance systems.
Xiaomi unveiled a family of in-house chips on Monday, marking a strategic shift toward vertical integration across its smartphone, AI device, and automotive divisions
1
. The announcement includes three distinct processors: the Xring O3 for smartphones, the Xring O100 AI accelerator, and the Xring D100 for intelligent driving applications2
. This represents over $3 billion in research and development investment, signaling Xiaomi's commitment to reducing reliance on external chip suppliers like Nvidia1
.
Source: InsideEVs
The Xring D100 chip addresses intelligent driving needs for Xiaomi's SU7 and YU7 electric vehicles, which currently depend on Nvidia's Drive Orin and Drive Thor hardware
1
. Built on a 3-nanometer process—reportedly the first mainland China chip at this node—the D100 features a 20-core CPU and 16-core NPU capable of supporting up to 160 gigabytes of unified memory1
. This configuration enables the chip to run 200-billion-parameter large AI models directly on-device without cloud connectivity1
2
. The D100 is scheduled for commercial deployment starting in 20272
.Comparing specifications reveals Xiaomi's ambitious positioning in custom silicon for AI. Nvidia's current Thor hardware offers a 14-core, 4-nanometer processor with up to 128GB of memory, while Tesla's Hardware 4 provides 16GB on a 7nm process
1
. Tesla's upcoming Hardware 5 targets a 2nm manufacturing process with 144GB of memory1
. However, Xiaomi has not disclosed the D100's Trillions of Operations Per Second (TOPS) rating, a critical performance metric for AI inference that determines real-world processing speed1
.The Xring O3 represents Xiaomi's first smartphone processor and will debut in the Xiaomi 18 Fold and Pad 9 Pro Max, launching in China this September
2
. The 3-nanometer chip features a 10-core all-big-core CPU paired with a 16-core G2-Ultra NX GPU, delivering 60% improved CPU performance, 85% better graphics, and 64% enhanced efficiency over previous generations2
. Critically, the O3 becomes Xiaomi's first chip supporting LPDDR6 memory with bandwidth rated at 113.8 GB/s2
.The Xring O100 functions as a dedicated AI chip built on a 6nm process, designed for on-device AI across smartphones, cars, and robots
2
. With 1.22 TB/s of near-memory bandwidth, the O100 enables local AI processing without cloud dependency2
. This AI accelerator approach mirrors strategies from other tech companies seeking to optimize performance for specific machine learning workloads while reducing power consumption1
.Related Stories
Xiaomi joins fellow Chinese manufacturers BYD, Nio, and Xpeng in developing proprietary chip design capabilities
1
. This trend accelerates as key players in the U.S. AI sector, including Anthropic's Dario Amodei, advocate for stricter export controls on AI compute technology1
. Designing chips in-house provides buffers against supply chain disruptions, rising AI chip costs, and potential trade restrictions while enabling manufacturers to optimize hardware specifically for their sensor suites, software architectures, and driving models1
.Control over chip development grants Xiaomi greater flexibility in cost management, supply chain resilience, and product development timing across its expanding ecosystem
1
. The immediate smartphone rollout with the O3 demonstrates Xiaomi's confidence in its chip design capabilities, while the delayed 2027 timeline for the D100 in advanced driver-assistance systems suggests the automotive application requires additional validation. Industry observers should monitor whether Xiaomi's custom silicon delivers competitive performance against established players like Nvidia and Tesla, particularly as TOPS ratings and real-world driving performance data emerge. The $3 billion investment signals long-term commitment, but success depends on execution quality and the company's ability to iterate rapidly in the fast-moving AI hardware landscape.Summarized by
Navi
[2]
20 Mar 2026•Technology

20 Aug 2026•Technology

30 Apr 2025•Technology

1
Technology

2
Technology

3
Technology
