Home / NVIDIA / NVIDIA GeForce RTX 6090: Performance and Specs

NVIDIA GeForce RTX 6090

NVIDIA GeForce RTX 6090
NVIDIA GeForce RTX 6090 graphics card review

NVIDIA GeForce RTX 6090: What the Rumors Say

The NVIDIA GeForce RTX 6090 has not been officially announced yet. Currently, the flagship of the GeForce line remains the RTX 5090 based on the Blackwell architecture, featuring 32 GB of GDDR7, so all information regarding the RTX 6090 should be taken as rumors.

According to leaks, the RTX 6090 may switch to the Rubin architecture or its gaming derivative. The GPU GR202 is mentioned, with up to 192 SM units, a 512-bit memory bus, and 32 GB of GDDR7. As with previous xx90 cards, NVIDIA might use a cut-down configuration rather than the full die.

The main focus, according to rumors, will not be on traditional rasterization but on ray tracing and path tracing. Some sources claim an increase of around 30-35% in traditional graphics and up to 2 times in path tracing compared to the RTX 50 Series. If this is true, the RTX 6090 will be a card not just for simple FPS gaming but for demanding modes with full ray tracing.

New 5th generation RT cores and 6th generation Tensor cores are expected. This makes sense as NVIDIA is increasingly moving towards neural network rendering, DLSS, frame generation, and AI acceleration. For gaming, this could mean more aggressive use of upscaling, frame generation, and path tracing instead of just increasing the number of CUDA cores.

The release date remains unclear. Earlier rumors pointed to a launch of the RTX 60 Series in the second half of 2027, but recent reports suggest a possible delay to 2028 due to memory shortages and prioritizing AI accelerators for data centers.

Summary of Rumors

Parameter Rumors
Architecture Rubin / gaming derivative of Rubin
GPU GR202
SM units Up to 192, likely not all active
Memory 32 GB GDDR7
Bus 512 bit
Focus path tracing, ray tracing, AI
RT cores 5th generation
Tensor cores 6th generation
Rasterization increase Approximately 30-35%
Path tracing increase Up to 2 times
Possible release 2027-2028, more often cited as 2028

Conclusion

The RTX 6090 currently appears to be a future ultra-flagship for 4K, 8K, path tracing, and AI tasks. However, specifics are scarce: there is no official date, price, or final specifications. The most plausible scenario is that NVIDIA will focus not on a sharp increase in traditional gaming performance, but on ray tracing, neural network rendering, and more powerful Tensor/RT cores.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
January 2027
Model Name
GeForce RTX 6090
Generation
GeForce 60
Base Clock
2300 MHz
Boost Clock
2700 MHz
Bus Interface
PCIe 5.0 x16
Transistors
Unknown
RT Cores
170
Tensor Cores
?
Tensor Cores are specialized processing units designed specifically for deep learning, providing higher training and inference performance compared to FP32 training. They enable rapid computations in areas such as computer vision, natural language processing, speech recognition, text-to-speech conversion, and personalized recommendations. The two most notable applications of Tensor Cores are DLSS (Deep Learning Super Sampling) and AI Denoiser for noise reduction.
680
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
680
Foundry
TSMC
Process Size
3 nm
Architecture
Rubin

Memory Specifications

Memory Size
32GB
Memory Type
GDDR7
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
512bit
Memory Clock
1750 MHz
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
1.79TB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
475.2 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
1836.0 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy.
117.5 TFLOPS
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
1.836 TFLOPS
FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
115.15 TFLOPS

Miscellaneous

SM Count
?
Multiple Streaming Processors (SPs), along with other resources, form a Streaming Multiprocessor (SM), which is also referred to as a GPU's major core. These additional resources include components such as warp schedulers, registers, and shared memory. The SM can be considered the heart of the GPU, similar to a CPU core, with registers and shared memory being scarce resources within the SM.
170
Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
21760
L1 Cache
128 KB (per SM)
L2 Cache
96 MB
TDP
525W
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.4
OpenCL Version
3.0
OpenGL
4.6
DirectX
12 Ultimate (12_2)
CUDA
12.0
Power Connectors
1x 16-pin
Shader Model
6.9
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
176
Suggested PSU
900 W

Benchmarks

FP32 (float)
Score
115.15 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS
Instinct MI300X
166.668 +44.7%
GeForce RTX 6090
115.15
TITAN Ada
91.042 -20.9%
Radeon Instinct MI300A
80.086 -30.5%
GeForce RTX 4080 Ti
66.228 -42.5%