Eyeq4 Datasheet
| Feature | EyeQ3 | EyeQ4 | EyeQ5 |
|---------|-------|-------|-------|
| Process node | 40nm | 28nm FD-SOI | 7nm FinFET |
| TOPS | 0.256 | 2.5 | 24 |
| Cameras supported | 1-2 | Up to 8 | Up to 16 |
| ASIL level | B | B (D for safety path) | B/D |
| Production start | 2014 | 2018 | 2021 |
Deep Learning Accelerator: Custom CNN accelerator
Image Processing: 2x multi-threaded VLIW cores for image filtering & scaling
Memory:
Safety: ASIL-B (ISO 26262) for the SoC, ASIL-D capable system with external components
For engineers reading an eyeq4 datasheet, the following electrical and physical parameters are critical: eyeq4 datasheet
| Parameter | Specification |
| :--- | :--- |
| Process Technology | 28nm CMOS (FinFET) |
| Maximum Camera Inputs | 8 simultaneous cameras |
| Processing Performance | 2.5 TOPS (Trillion Operations Per Second) |
| Power Consumption | 3W – 5W (typical thermal design power) |
| Operating Temperature | -40°C to +125°C (Automotive Grade) |
| Safety Certification | ASIL-B (ISO 26262) |
| Package Type | BGA (Ball Grid Array) – 585 pin variant |
| Interface Support | CAN-FD, FlexRay, Gigabit Ethernet, LVDS, I2C, SPI, GPIO | | Feature | EyeQ3 | EyeQ4 | EyeQ5
| Function | Benefit |
|----------|---------|
| 5–8 camera fusion | Reduces blind spots, enables 360° perception |
| Hardware CNN engine | Runs semantic segmentation + object detection without choking the CPU |
| Internal ISP + HDR | Works with 1 MP–8 MP sensors without external ISP | Safety: ASIL-B (ISO 26262) for the SoC, ASIL-D
Here is the datasheet text for the EyeQ4 (by Mobileye, an Intel company). This is a technical summary based on public and industry-standard documentation.
From the official datasheet summary and ISO 26262-compliant documentation:
| Feature | EyeQ3 | EyeQ4 | EyeQ5 |
|---------|-------|-------|-------|
| Process node | 40nm | 28nm FD-SOI | 7nm FinFET |
| TOPS | 0.256 | 2.5 | 24 |
| Cameras supported | 1-2 | Up to 8 | Up to 16 |
| ASIL level | B | B (D for safety path) | B/D |
| Production start | 2014 | 2018 | 2021 |
Deep Learning Accelerator: Custom CNN accelerator
Image Processing: 2x multi-threaded VLIW cores for image filtering & scaling
Memory:
Safety: ASIL-B (ISO 26262) for the SoC, ASIL-D capable system with external components
For engineers reading an eyeq4 datasheet, the following electrical and physical parameters are critical:
| Parameter | Specification |
| :--- | :--- |
| Process Technology | 28nm CMOS (FinFET) |
| Maximum Camera Inputs | 8 simultaneous cameras |
| Processing Performance | 2.5 TOPS (Trillion Operations Per Second) |
| Power Consumption | 3W – 5W (typical thermal design power) |
| Operating Temperature | -40°C to +125°C (Automotive Grade) |
| Safety Certification | ASIL-B (ISO 26262) |
| Package Type | BGA (Ball Grid Array) – 585 pin variant |
| Interface Support | CAN-FD, FlexRay, Gigabit Ethernet, LVDS, I2C, SPI, GPIO |
| Function | Benefit |
|----------|---------|
| 5–8 camera fusion | Reduces blind spots, enables 360° perception |
| Hardware CNN engine | Runs semantic segmentation + object detection without choking the CPU |
| Internal ISP + HDR | Works with 1 MP–8 MP sensors without external ISP |
Here is the datasheet text for the EyeQ4 (by Mobileye, an Intel company). This is a technical summary based on public and industry-standard documentation.
From the official datasheet summary and ISO 26262-compliant documentation: