GeForce RTX 4070 Mobile
Graphics Card GeForce RTX 4070 Mobile — Specifications, Tests & Benchmarks
GeForce RTX 4070 Mobile
Nvidia GeForce 40 Mobile
•
AD106
•
03.01.2023
•
8 GB
•
GDDR6
•
128 bit
•
115W
🏆 Top #5543
Performance
Synthetic Score
15,225
PassMark
19,537
Efficiency
high
The GeForce RTX 4070 Mobile (Ada Lovelace) model joined the NVIDIA lineup of graphics accelerators on 03.01.2023. The graphics processor is manufactured using a modern process. The 188 mm² die contains approximately 22.9 billion transistorsistors transistors. The model's computational arsenal includes 4608 universal processors. Also available are 36 specialized cores for ray rendering and 144 cores for accelerating artificial intelligence. The graphics card is equipped with 8 GB of GDDR6 memory. A 128 bit-bit bus is used, providing bandwidth at 256.00 GB/s. The GPU's base clock speed is 1395 MHz, and in Boost mode, it can automatically increase up to 1695 MHz. The nominal thermal design power is 115 W. For stable system operation, a PSU of 0 W or more will be required.
General Information
| Release Date | 03.01.2023 |
| Production Status | Active |
| Usage Class | Hardcore Gaming |
| Market Segment | Mobile / Laptop |
| Series | Nvidia GeForce 40 Mobile |
| GPU Variant | GN21-X6 |
| Integrated Graphics | Yes |
GPU
| Architecture | Ada Lovelace |
| Codename | AD106 |
| Process Node | 5 nm (TSMC) |
| Transistor Count | 22,900,000.0 million |
| Die Size | 188 mm² |
| Transistor Density | 121,800,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 4608 |
| Texture Mapping Units (TMU) | 144 |
| Render Output Units (ROP) | 48 |
| Tensor Cores | 144 |
| RT Cores (Ray Tracing) | 36 |
| Compute Units (SM/CU) | 36 |
Clock Speeds
| Base Clock | 1395 MHz |
| Boost Clock | 1695 MHz |
| Memory Clock (Actual) | 2000 MHz |
| Memory Clock (Effective) | 16000 MHz |
Memory
| Memory Capacity | 8 GB |
| Memory Type | GDDR6 |
| Memory Bus | 128 bit bit |
| Memory Bandwidth | 256.00 GB/s |
Cache Memory
| L1 Cache | 4608 KB |
| L2 Cache | 32 MB |
Board Design & Power
| Interface | PCIe 4.0 x8 |
| Slot Width | 0 |
| Power Consumption (TDP) | 115 W |
API Support
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.4 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 81360 GPixel/s |
| Texture Fill Rate | 244100 GTexel/s |
| FP16 Performance (Half) | 15.62 TFLOPS (1:1) |
| FP32 Performance (Float) | 15.62 TFLOPS |
| FP64 Performance (Double) | 244.1 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 19 537 |
| PassMark (G2D Mark) | 767 |
| TPU Index Score | 21.68% |
| Performance Tier | high |
Всі тести
Тестів поки немає.
Comments
0Please log in to your account to leave a comment.
Log In or RegisterNo comments yet. Be the first to comment!
Are you sure you want to delete this comment? This action cannot be undone.