NVIDIA 8x GeForce RTX 5090 vs NVIDIA GeForce RTX 2080 Super
NVIDIA 8x GeForce RTX 5090
$15,992
NVIDIA GeForce RTX 2080 Super
$699
|
8x 21760 Shaders
256GB (8x 32GB) GDDR7
2407MHz
|
3072 Shaders
8GB GDDR6
1815MHz
|
|
Peak AI Performance
26.82 PFLOPS
FP4 Tensor Sparse
|
Peak AI Performance
356.84 TOPS
INT4 Tensor
|
|
FP32
838.02 TFLOPS
|
FP32
11.15 TFLOPS
|
|
FP16
838.02 TFLOPS
|
FP16
22.3 TFLOPS
|
|
Form Factor
PCIe Card
8x 2.1-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
4600W
|
TDP
250W
|
|
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
|
Power Connectors
1x 6-Pin
1x 8-Pin
-
-
|
|
GB6 OpenCL N/A
0%
|
|
|
GB6 Metal N/A
0%
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL N/A
0%
|
GB5 OpenCL 113,040
37%
|
|
GB5 CUDA N/A
0%
|
GB5 CUDA 126,140
36%
|
|
GB5 Metal N/A
0%
|
GB5 Metal N/A
0%
|
|
GB5 Vulkan N/A
0%
|
GB5 Vulkan 93,765
46%
|
|
OCT 2020.1 N/A
0%
|
OCT 2020.1 275
36%
|
|
OCT Metal N/A
0%
|
OCT Metal N/A
0%
|
|
Peak AI
Performance
26.82 PFLOPS
FP4 Tensor Sparse
|
Peak AI
Performance
356.84 TOPS
INT4 Tensor
|
|
FP4
13.41 PFLOPS
Tensor
26.82 PFLOPS
Tensor Sparse
|
-
-
-
|
|
FP8
-
6.7 PFLOPS
Tensor (FP16 Accumulate)
13.41 PFLOPS
Tensor (FP16 Accumulate) Sparse
3.35 PFLOPS
Tensor (FP32 Accumulate)
6.7 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
-
-
-
-
-
-
|
|
FP16
838.02 TFLOPS
3.35 PFLOPS
Tensor (FP16 Accumulate)
6.7 PFLOPS
Tensor (FP16 Accumulate) Sparse
1.68 PFLOPS
Tensor (FP32 Accumulate)
3.35 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP16
22.3 TFLOPS
89.21 TFLOPS
Tensor (FP16 Accumulate)
-
44.61 TFLOPS
Tensor (FP32 Accumulate)
-
|
|
FP32
838.02 TFLOPS
-
-
|
FP32
11.15 TFLOPS
-
-
|
|
FP64
13.1 TFLOPS
-
|
FP64
350 GFLOPS
-
|
|
BF16
838.02 TFLOPS
1.68 PFLOPS
Tensor
3.35 PFLOPS
Tensor Sparse
|
BF16
-
44.61 TFLOPS
Tensor
-
|
|
TF32
838.02 TFLOPS
Tensor
1.68 PFLOPS
Tensor Sparse
|
TF32
44.61 TFLOPS
Tensor
-
|
|
-
-
-
|
INT4
356.84 TOPS
Tensor
-
|
|
INT8
-
6.7 POPS
Tensor
13.41 POPS
Tensor Sparse
|
INT8
-
178.42 TOPS
Tensor
-
|
|
INT32
838.02 TOPS
|
INT32
11.15 TOPS
|
|
Ray Tracing
317.7 TOPS
|
Ray Tracing
33.6 TOPS
|
|
Pixel
Fillrate
423.632 GPixel/s
|
Pixel
Fillrate
116.16 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
1636.76 GTexel/s
|
Texture
Fillrate
348.48 GTexel/s
|
|
Manufacturer
NVIDIA
|
Manufacturer
NVIDIA
|
|
Chip Designer
NVIDIA
|
Chip Designer
NVIDIA
|
|
Architecture
Blackwell
|
Architecture
Turing
|
|
Family
GeForce 50
|
Family
GeForce 20
|
|
Codename
NV192
GB202
Variant
GB202-300-A1
|
Codename
NV164
TU104
Variant
TU104-450-A1
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
1/6/2025
|
Release Date
7/23/2019
|
|
Foundry
TSMC
-
|
Foundry
TSMC
-
|
|
Fabrication Node
4NP
-
|
Fabrication Node
12FFN
-
|
|
Die Size
8x 762 mm²
-
|
Die Size
545 mm²
-
|
|
Transistor Count
8x 92.2 Billion
-
|
Transistor Count
13.6 Billion
-
|
|
Transistor Density
121.07M/mm²
-
|
Transistor Density
24.95M/mm²
-
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
8x 21760 Shaders
-
|
Shading Units
3072 Shaders
-
|
|
Texture Mapping Units
8x 680 TMUs
|
Texture Mapping Units
192 TMUs
|
|
Render Output Units
8x 176 ROPs
|
Render Output Units
64 ROPs
|
|
Tensor Cores
8x 680 T-Cores
|
Tensor Cores
384 T-Cores
|
|
Ray-Tracing Cores
8x 170 RT-Cores
|
Ray-Tracing Cores
48 RT-Cores
|
|
Streaming Multiprocessors
8x 170 SMs
|
Streaming Multiprocessors
48 SMs
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Graphics Processing Clusters
8x 11 GPCs
|
Graphics Processing Clusters
6 GPCs
|
|
-
-
2010MHz Base
2407MHz
|
-
-
1650MHz Base
1815MHz
|
|
-
-
|
-
-
|
|
L1
64KB/SM Tex
128KB/SM
-
-
|
L1
32KB/SM Tex
64KB/SM
-
-
|
|
L2
96MB Shared
|
L2
4MB Shared
|
|
-
-
-
|
-
-
-
|
|
256GB (8x 32GB)
GDDR7
-
|
8GB
GDDR6
-
|
|
Bus Width
512Bit
|
Bus Width
256Bit
|
|
Clock
1750MHz
Transfer Rate
28GT/s
Bandwidth
1792GB/s
|
Clock
1940MHz
Transfer Rate
15.5GT/s
Bandwidth
496.6GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
4600W
|
TDP
250W
|
|
Temp
90°C Max
|
Temp
89°C Max
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
24x DisplayPort 2.1
-
-
-
-
-
-
-
-
-
8x HDMI 2.1
-
-
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
3x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
1x HDMI 2.0
-
1x USB-C + DP
-
|
|
Max Resolution
7680x4320
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
165Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
4
|
Multi Monitor Support
4
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.2
|
|
Model
3x NVENC 9
|
Model
NVENC 7
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
2x NVDEC 6
|
Model
NVDEC 4
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Direct X
12
Direct 3D
12_3
|
Direct X
12
Direct 3D
12_2
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.8
CUDA
12.8
-
-
PureVideo HD
VP13
VDPAU
Feature Set M
|
Shader Model
6.6
CUDA
7.5
-
-
PureVideo HD
VP10
VDPAU
Feature Set J
|
|
-
-
-
2x Fans
|
-
-
-
2x Fans
|
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
Power Connectors
-
-
1x 6-Pin
1x 8-Pin
-
-
-
|
|
Slots Required
2.1
PCIe Version
5.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
|
|
-
-
-
-
|
Multi GPU Support
Supported
Type
2-way NVLink
|
|
Height
137 mm (5.39 in)
Width
304 mm (11.97 in)
Depth
42 mm (1.65 in)
|
Height
115.7 mm (4.56 in)
Width
266.7 mm (10.5 in)
Depth
35 mm (1.38 in)
|
Copy Link