Company
EyeQ™
High-performance, cost-optimized
silicon for next-gen ADAS & AV
Scalable autonomy starts with the Mobileye EyeQ™ system-on-chip. Purpose-built for automotive-grade applications, EyeQ combines hardware and software in a high-efficiency, low-power design. This cost-optimized silicon powers a modular portfolio— enabling automakers to scale next-generation driver-assist and autonomous driving programs.
THE EYEQ™ PORTFOLIO
Smart compute for safer mobility
Smart compute for safer mobility
Mobileye’s EyeQ™ family of system-on-chip solutions powers solutions ranging from advanced driver-assistance to full autonomy. Purpose-built for automotive-grade applications, each EyeQ™ integrates custom hardware and software to deliver high performance, low power consumption, and real-time responsiveness.
With a scalable architecture and dedicated AI acceleration, EyeQ™ enables intelligent workload distribution across complex driving tasks - supporting a broad spectrum of vehicle platforms and mobility functions. From front-facing camera systems to fully autonomous vehicles, EyeQ™ is the compute foundation behind Mobileye’s advanced vision and decision-making technologies.
EyeQ™ 6
The new standard for efficiency in driver assistance
EyeQ™ 6 High
Premium ADAS /AV partial or full surround
Eyes-on
Hands-on
Eyes-on
Hands-off
Eyes-off
Hands-off
No driver
Driver visualization
Park assist
34 DL TOPS (int8) 7nm
2x EyeQ™ 6 High powering
Mobileye SuperVision™ >3x EyeQ™ 6 High powering
Mobileye Chauffeur™ >4x EyeQ™ 6 High powering
Mobileye Drive™ >
Hover over the image to explore the schematics
EyeQ6H vs. NVIDIA Jetson AGX Orin
Benchmark here
EyeQ™ 6 Lite
ADAS front camera
Eyes-on
Hands-on
Higher compute in a smaller package
One-box windshield solution
5 DL TOPS (int8) 7nm
Hover over the image to explore the schematics
EyeQ™ 6
The new standard for efficiency in driver assistance
EyeQ™ 6 High
Premium ADAS /AV partial or full surround
Eyes-on
Hands-on
Eyes-on
Hands-off
Eyes-off
Hands-off
No driver
Driver visualization
Park assist
34 DL TOPS (int8) 7nm
2x EyeQ™ 6 High powering
Mobileye SuperVision™ >3x EyeQ™ 6 High powering
Mobileye Chauffeur™ >4x EyeQ™ 6 High powering
Mobileye Drive™ >EyeQ6H vs. NVIDIA Jetson AGX Orin
Benchmark here
EyeQ™ 6 Lite
ADAS front camera
Eyes-on
Hands-on
Higher compute in a smaller package
One-box windshield solution
5 DL TOPS (int8) 7nm
EyeQ™ 5
Premium SoCs with autonomous capabilities
EyeQ™ 5 Mid
High-end ADAS/AV front camera
EyeQ™ 5 High
ADAS/AV partial or full surround
EyeQ™ 4
The trusted SoCs for driver-assist solutions
EyeQ™ 4 Mid
ADAS front camera
EyeQ™ 4 High
ADAS/AV trifocal
20 years, more than 200 million
vehicles on the road
20 years, more than 200 million vehicles on the road
In over 20 years of technological advancement, EyeQ™ has emerged as the trusted solution for processing advanced mobility technologies.
200M
EyeQs shipped
to date
1200
Models on the market
incorporating EyeQ™
50+
Automakers place
their trust in EyeQ™
6
Generations
of EyeQ™
Architecture of Efficiency
With a unique and highly efficient architecture of diversified accelerators, EyeQ™ achieves state-of-the-art computer vision performance within a low-power envelope
Heterogeneous Computing
Using the most suitable core for each task
From general-purpose CPU cores to high compute density accelerators, including deep learning neural networks
CPU
Central Processing Unit
MPC
Multi-threaded Processor Cluster
More versatile than a GPU, and with higher efficiency than any CPU
VMP
Vector Microcode Processor
A wide vector (VLIW and SIMD) machine with exceptional performance for short integral types common in computer vision and deep learning algorithms.
PMA
Programmable Macro Array
A CGRA dataflow machine. Its unique architecture delivers outstanding performance for dense computer vision and deep learning algorithms that are unachievable in classic DSP architecture.
XNN
Deep Learning Accelerator
Dedicated high-performance AI engine. The main source of horse power for convolutional neural networks.
GENERAL-PURPOSE COMPUTE
CPU
Central Processing Unit
MPC
Multi-threaded Processor Cluster
More versatile than a GPU, and with higher efficiency than any CPU
VMP
Vector Microcode Processor
A wide vector (VLIW and SIMD) machine with exceptional performance for short integral types common in computer vision and deep learning algorithms.
PMA
Programmable Macro Array
A CGRA dataflow machine. Its unique architecture delivers outstanding performance for dense computer vision and deep learning algorithms that are unachievable in classic DSP architecture.
XNN
Deep Learning Accelerator
Dedicated high-performance AI engine. The main source of horse power for convolutional neural networks.
DL PERFORMANCE / COMPUTE DENSITY
Scalable Architecture
Utilizing the right mixture of accelerators to match the different EyeQ™ model needs
Designing EyeQ’s hardware architecture with its intended software needs in mind, along with these heterogeneous accelerators, enables EyeQ™ to provide unparalleled performance, while requiring fewer TOPS and consuming less power
Ultimate
Cost-Performance
Ratio
EyeQ™ in Action
Watch how the highly efficient, scalable, and proven technology of EyeQ™ enables our developmental self-driving vehicle to operate seamlessly in real-world traffic.
Full support for developing
third-party applications
with EyeQ Kit™
The newest generations of EyeQ™ support open compute by offering a user-friendly software development kit (SDK), allowing customers to differentiate their solutions by deploying their algorithms on EyeQ™.
Learn more about EyeQ Kit™
Full support for developing third-party applications with EyeQ Kit™
The newest generations of EyeQ™ support open compute by offering a user-friendly software development kit (SDK), allowing customers to differentiate their solutions by deploying their algorithms on EyeQ™.
Learn more about EyeQ Kit™
