GeForce RTX 3070 Ti
Graphics Card GeForce RTX 3070 Ti — Specifications, Tests & Benchmarks
GeForce RTX 3070 Ti
Nvidia GeForce 30
•
GA104
•
31.05.2021
•
8 GB
•
GDDR6X
•
256 bit
•
290W
🏆 Top #1754
Performance
Synthetic Score
26,304
PassMark
23,276
Efficiency
high
The GeForce RTX 3070 Ti graphics adapter is based on the advanced Ampere architecture. NVIDIA announced this model on 31.05.2021. The graphics processor is manufactured using a modern process. The 392 mm² die contains approximately 17.4 billion transistorsistors transistors. The core configuration includes 6144 shader units, 48 RT Cores for ray tracing, and 192 Tensor Cores for AI tasks. The memory subsystem features GDDR6X modules with a total capacity of 8 GB. The bus width is 256 bit bits, and the peak data exchange rate is 608.30 GB/s. The GPU's base clock speed is 1575 MHz, and in Boost mode, it can automatically increase up to 1770 MHz. The nominal thermal design power is 290 W. For stable system operation, a PSU of 600 W or more will be required.
General Information
| Release Date | 31.05.2021 |
| Usage Class | Hardcore Gaming |
| Market Segment | Desktop |
| Series | Nvidia GeForce 30 |
| GPU Variant | GA104-400-A1 |
GPU
| Architecture | Ampere |
| Codename | GA104 |
| Process Node | 8 nm (Samsung) |
| Transistor Count | 17,400,000.0 million |
| Die Size | 392 mm² |
| Transistor Density | 44,400,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 6144 |
| Texture Mapping Units (TMU) | 192 |
| Render Output Units (ROP) | 96 |
| Tensor Cores | 192 |
| RT Cores (Ray Tracing) | 48 |
| Compute Units (SM/CU) | 48 |
Clock Speeds
| Base Clock | 1575 MHz |
| Boost Clock | 1770 MHz |
| Memory Clock (Actual) | 1188 MHz |
| Memory Clock (Effective) | 19000 MHz |
Memory
| Memory Capacity | 8 GB |
| Memory Type | GDDR6X |
| Memory Bus | 256 bit bit |
| Memory Bandwidth | 608.30 GB/s |
Cache Memory
| L1 Cache | 6144 KB |
| L2 Cache | 4 MB |
Board Design & Power
| Interface | PCIe 4.0 x16 |
| Slot Width | 2 |
| Dimensions (L x W x H) | |
| Power Consumption (TDP) | 290 W |
| Recommended PSU | 600 W |
| Power Connectors | 1x 12-pin |
| Board Number | PG143 SKU 15 |
API Support
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.4 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 169900 GPixel/s |
| Texture Fill Rate | 339800 GTexel/s |
| FP16 Performance (Half) | 21.75 TFLOPS (1:1) |
| FP32 Performance (Float) | 21.75 TFLOPS |
| FP64 Performance (Double) | 339.8 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 23 276 |
| PassMark (G2D Mark) | 1 061 |
| TPU Index Score | 33.12% |
| 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.