AX Gaming RTX 5070 Ti X3W
Graphics Card AX Gaming RTX 5070 Ti X3W — Specifications, Tests & Benchmarks
AX Gaming RTX 5070 Ti X3W
Nvidia GeForce 50
•
GB203
•
20.02.2025
•
16 GB
•
GDDR7
•
256 bit
•
300W
🏆 Top #819
Performance
Synthetic Score
32,473
PassMark
32,473
Efficiency
enthusiast
The AX Gaming RTX 5070 Ti X3W graphics adapter is based on the advanced Blackwell 2.0 architecture. NVIDIA announced this model on 20.02.2025. Thanks to 4N FinFET manufacturing technology, engineers managed to place 45.6 billion transistorsistors transistors on a 378 mm² die. For graphics processing, 8960 shader units are provided. The technological equipment is complemented by 70 RT Cores and 280 Tensor Cores. The GDDR7 video memory capacity is 16 GB. Thanks to the 256 bit-bit bus, bandwidth reaches 896.00 GB/s, eliminating delays when working with demanding textures. In standard mode, the core operates at 2295 MHz, but auto-overclocking technology allows it to reach 2452 MHz under load. The nominal thermal design power is 300 W. For stable system operation, a PSU of 700 W or more will be required.
General Information
| Release Date | 20.02.2025 |
| Production Status | Active |
| Usage Class | Hardcore Gaming |
| Market Segment | Desktop |
| Series | Nvidia GeForce 50 |
| GPU Variant | GB203-300-A1 |
GPU
| Architecture | Blackwell 2.0 |
| Codename | GB203 |
| Process Node | 5 nm (TSMC) |
| Process Type | 4N FinFET |
| Transistor Count | 45,600,000.0 million |
| Die Size | 378 mm² |
| Transistor Density | 120,600,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 8960 |
| Texture Mapping Units (TMU) | 280 |
| Render Output Units (ROP) | 96 |
| Tensor Cores | 280 |
| RT Cores (Ray Tracing) | 70 |
| Compute Units (SM/CU) | 70 |
Clock Speeds
| Base Clock | 2295 MHz |
| Boost Clock | 2452 MHz |
| Memory Clock (Actual) | 1750 MHz |
| Memory Clock (Effective) | 28000 MHz |
Memory
| Memory Capacity | 16 GB |
| Memory Type | GDDR7 |
| Memory Bus | 256 bit bit |
| Memory Bandwidth | 896.00 GB/s |
Cache Memory
| L1 Cache | 8960 KB |
| L2 Cache | 48 MB |
Board Design & Power
| Interface | PCIe 5.0 x16 |
| Slot Width | 3 |
| Dimensions (L x W x H) | 316 x 65 x 131 mm |
| Power Consumption (TDP) | 300 W |
| Recommended PSU | 700 W |
| Power Connectors | 1x 16-pin |
| Board Number | PG147 SKU 60 |
API Support
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.4 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 235.4 GPixel/s |
| Texture Fill Rate | 686.6 GTexel/s |
| FP16 Performance (Half) | 43.94 TFLOPS (1:1) |
| FP32 Performance (Float) | 43.94 TFLOPS |
| FP64 Performance (Double) | 686.6 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 32 473 |
| PassMark (G2D Mark) | 1 333 |
| TPU Index Score | 57.46% |
| Performance Tier | enthusiast |
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.