KFA2 RTX 3070 Ti SG (1-Click OC)
Graphics Card KFA2 RTX 3070 Ti SG (1-Click OC) — Specifications, Tests & Benchmarks
KFA2 RTX 3070 Ti SG (1-Click OC)
Nvidia GeForce 30
•
GA104
•
31.05.2021
•
8 GB
•
GDDR6X
•
256 bit
•
290W
🏆 Top #1653
Performance
Synthetic Score
26,749
PassMark
23,276
Efficiency
high
The KFA2 RTX 3070 Ti SG (1-Click OC) graphics card from NVIDIA is built on the Ampere architecture and was officially introduced on 31.05.2021. Thanks to modern manufacturing technology, engineers managed to place 17.4 billion transistorsistors transistors on a 392 mm² die. The model's computational arsenal includes 6144 universal processors. Also available are 48 specialized cores for ray rendering and 192 cores for accelerating artificial intelligence. The GDDR6X video memory capacity is 8 GB. Thanks to the 256 bit-bit bus, bandwidth reaches 608.30 GB/s, eliminating delays when working with demanding textures. The graphics chip operates at a base clock of 1575 MHz with dynamic acceleration capability up to 1800 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 | 1800 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 | 3 |
| Dimensions (L x W x H) | 317 x 61 x 113 mm |
| Power Consumption (TDP) | 290 W |
| Recommended PSU | 600 W |
| Power Connectors | 2x 8-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 | 172.8 GPixel/s |
| Texture Fill Rate | 345.6 GTexel/s |
| FP16 Performance (Half) | 22.12 TFLOPS (1:1) |
| FP32 Performance (Float) | 22.12 TFLOPS |
| FP64 Performance (Double) | 345.6 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 23 276 |
| PassMark (G2D Mark) | 1 061 |
| TPU Index Score | 33.68% |
| Performance Tier | high |
How this graphics card performs in games
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.