Explore the complete details of GeForce RTX 5090, including specs, performance benchmarks
The GeForce RTX 5090 GPU by NVIDIA. features a Blackwell 2.0 (2025) architecture. with 21760 CUDA cores. and a boost clock of 2407 MHz MHz. It offers GDDR7 memory with 32 GB GB capacity and a 512 Bit-bit interface. delivering a bandwidth of 1.79 TB/s GB/s. With a power consumption (TDP) of 575W. it supports DirectX 12 Ultimate (12_2), Vulkan 1.4, DLSS 1 for enhanced performance.
Basic details about the GeForce RTX 5090, including manufacturer, ranking, and release date.
Title | GeForce RTX 5090 |
---|---|
Manufacturer | NVIDIA |
Ranking | 2 |
Popularity Rank | 25 |
Architecture | Blackwell 2.0 (2025) |
GPU code name | GB202 |
Market Segmente | Desktop |
Length - Width | 304 mm - 2-slot |
Release Date | 30 January 2025 |
Launch Price | $N/A |
Details on clock speeds, cores, and floating-point processing power of GeForce RTX 5090.
Core Clock Speed | 2017 MHz |
---|---|
Boost Clock Speed | 2407 MHz |
Floating Point Processing Power | 104.8 TFLOPS |
No of Transistors | 92,200 million |
CUDA Cores | 21760 |
Ray Tracing Cores | 170 |
Tensor Cores | 680 |
Texture Fill Rate | 1,637 |
ROPs | 176 |
GPU Model | DLSS Support | Ray Tracing | Tensor Cores | Resizable BAR | HDMI Support |
---|---|---|---|---|---|
GeForce RTX 5090 |
✓ Yes
|
170
|
680
|
✓ Yes
|
✓ Yes
|
GeForce RTX 5050 |
✓ Yes
|
20
|
80
|
✓ Yes
|
✓ Yes
|
GeForce RTX 5060 |
✓ Yes
|
30
|
120
|
✓ Yes
|
✓ Yes
|
GeForce RTX 5060 Ti 16 GB |
✓ Yes
|
36
|
144
|
✓ Yes
|
✓ Yes
|
GeForce RTX 5060 Ti |
✓ Yes
|
36
|
144
|
✓ Yes
|
✓ Yes
|
GeForce RTX 5060 Ti 8 GB |
✓ Yes
|
36
|
144
|
✓ Yes
|
✓ Yes
|
Available display connectors and API compatibility for enhanced performance.
Interface | PCIe 5.0 x16 |
---|---|
Display Connectors | 1x HDMI 2.1b, 3x DisplayPort 2.1b |
HDMI | 1 |
DirectX | 12 Ultimate (12_2) |
Shader Model | 6.8 |
OpenGL | 4.6 |
OpenCL | 3.0 |
Vulkan | 1.4 |
CUDA | 12.0 |
DLSS | 1 |
TMUs | 680 |
Information on memory type, capacity, and bandwidth to evaluate data processing power.
Memory Type | GDDR7 |
---|---|
Maximum RAM | 32 GB |
Memory Bus Width | 512 Bit |
Memory Clock Speed | 1750 MHz |
Memory Bandwidth | 1.79 TB/s GB/s |
Resizable BAR | 1 |
Power consumption, efficiency, and additional power requirements.
Power Consumption (TDP) | 575 W |
---|---|
Power Efficiency | 12.41 |
Manufacturing Process | 5 nm |
Supplementary Power Connectors | 1x 16-pin |
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.
Estimated FPS in popular games at different resolutions and settings.
4K Ultra settings, high FPS gaming
AI-accelerated editing, 3D rendering
CAD, scientific computing
1150W
304 mm
PCIe 5.0 x16
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.
The GeForce RTX 5090 is a graphics card manufactured by NVIDIA, released on 30 January 2025. Currently ranked #2 in our comprehensive graphics card rankings, this GPU has achieved an impressive performance score of 93.58 points, solidifying its position as a high-performance graphics solution.
Architecture: Built on the Blackwell 2.0 (2025) architecture with the GB202 GPU core.
Manufacturing Process: Manufactured using cutting-edge 5 nm process technology, ensuring optimal power efficiency and performance density.
Processing Cores: Features 21760 processing cores (CUDA cores), providing substantial parallel processing capabilities for both gaming and compute workloads.
Clock Speeds: Base clock operates at 2017 MHz, with boost clocks reaching up to 2407 MHz, delivering consistent high-performance gaming and rendering capabilities.
Compute Performance: Delivers 104.8 TFLOPS of floating-point processing power, making it suitable for both gaming and professional applications.
Texture Performance: With a texture fill rate of 1,637, this GPU excels at rendering detailed textures and complex visual effects.
Memory Specifications: Equipped with 32 GB of high-speed GDDR7 memory connected via a 512 Bit-bit memory bus, providing 1.79 TB/s of memory bandwidth.
Power Consumption: Operates with a Total Graphics Power (TGP) of 575, achieving excellent power efficiency ratings.
Power Requirements: Requires 1x 16-pin for stable operation, ensuring adequate power delivery for peak performance scenarios.
Ray Tracing: Dedicated ray tracing cores (170) enable real-time ray tracing for photorealistic lighting and reflections.
AI Acceleration: Tensor cores (680) provide AI and machine learning acceleration.
DLSS Support: 1 technology support for enhanced performance without compromising visual quality.
Resizable BAR: 1 support for improved CPU-GPU communication.
Display Outputs: Features 1x HDMI 2.1b, 3x DisplayPort 2.1b display connectors including 1 support for versatile multi-monitor setups.
Graphics API Support: Supports DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4, CUDA 12.0 for broad compatibility with modern games and applications.
Positioned in the Desktop market segment, Currently ranked #25 in popularity among enthusiasts and gamers, making it a competitive choice in its category.
The GeForce RTX 5090 represents NVIDIA's commitment to delivering high-performance graphics solutions. With its advanced ray tracing capabilities, impressive power efficiency, generous memory allocation, this GPU is well-suited for demanding gaming scenarios, content creation, and professional workloads. Whether you're a competitive gamer, content creator, or enthusiast, the GeForce RTX 5090 offers the performance and features needed to handle today's most demanding visual applications.