Inno3D RTX 5090 iCHILL FROSTBITE PRO
Graphics Card Inno3D RTX 5090 iCHILL FROSTBITE PRO — Specifications, Tests & Benchmarks
Inno3D RTX 5090 iCHILL FROSTBITE PRO
Nvidia GeForce 50
•
GB202
•
30.01.2025
•
32 GB
•
GDDR7
•
512 bit
•
575W
🏆 Top #262
Performance
Synthetic Score
38,898
PassMark
38,898
Efficiency
enthusiast
Inno3D RTX 5090 iCHILL FROSTBITE PRO is a powerful solution from NVIDIA based on the Blackwell 2.0 architecture, released on 30.01.2025. The graphics processor is manufactured using a 4N FinFET process. The 750 mm² die contains approximately 92.2 billion transistorsistors transistors. The core configuration includes 21760 shader units, 170 RT Cores for ray tracing, and 680 Tensor Cores for AI tasks. The GDDR7 video memory capacity is 32 GB. Thanks to the 512 bit-bit bus, bandwidth reaches 1832.96 GB/s, eliminating delays when working with demanding textures. In standard mode, the core operates at 2017 MHz, but auto-overclocking technology allows it to reach 2407 MHz under load. The TDP level for this model is 575 W, so for a build, it\'s advisable to choose quality cooling and a power supply unit of at least 950 W.
General Information
| Release Date | 30.01.2025 |
| Production Status | Active |
| Usage Class | Hardcore Gaming |
| Market Segment | Desktop |
| Series | Nvidia GeForce 50 |
| GPU Variant | GB202-300-A1 |
GPU
| Architecture | Blackwell 2.0 |
| Codename | GB202 |
| Process Node | 5 nm (TSMC) |
| Process Type | 4N FinFET |
| Transistor Count | 92,200,000.0 million |
| Die Size | 750 mm² |
| Transistor Density | 122,900,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 21760 |
| Texture Mapping Units (TMU) | 680 |
| Render Output Units (ROP) | 176 |
| Tensor Cores | 680 |
| RT Cores (Ray Tracing) | 170 |
| Compute Units (SM/CU) | 170 |
Clock Speeds
| Base Clock | 2017 MHz |
| Boost Clock | 2407 MHz |
| Memory Clock (Actual) | 1750 MHz |
| Memory Clock (Effective) | 28000 MHz |
Memory
| Memory Capacity | 32 GB |
| Memory Type | GDDR7 |
| Memory Bus | 512 bit bit |
| Memory Bandwidth | 1832.96 GB/s |
Cache Memory
| L1 Cache | 21760 KB |
| L2 Cache | 96 MB |
Board Design & Power
| Interface | PCIe 5.0 x16 |
| Slot Width | 1 |
| Dimensions (L x W x H) | 223 x 20 x 134 mm |
| Power Consumption (TDP) | 575 W |
| Recommended PSU | 950 W |
| Power Connectors | 1x 16-pin |
| Board Number | PG145 SKU 30 |
API Support
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.4 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 423.6 GPixel/s |
| Texture Fill Rate | 636.8 GTexel/s |
| FP16 Performance (Half) | 104.80 TFLOPS (1:1) |
| FP32 Performance (Float) | 104.80 TFLOPS |
| FP64 Performance (Double) | 1.64 TFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 38 898 |
| PassMark (G2D Mark) | 1 411 |
| TPU Index Score | 100.00% |
| Performance Tier | enthusiast |
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.