NVIDIA GeForce RTX 5090 vs AMD Radeon RX 9070 XT
NVIDIA GeForce RTX 5090
$1,999
AMD Radeon RX 9070 XT
$599
|
21760 Shaders
32GB GDDR7
2407MHz
|
4096 Shaders
16GB GDDR6
2970MHz
|
|
Peak AI Performance
3.35 PFLOPS
FP4 Tensor Sparse
|
Peak AI Performance
1.56 POPS
INT4 Tensor Sparse
|
|
FP32
104.75 TFLOPS
|
FP32
48.66 TFLOPS
|
|
FP16
104.75 TFLOPS
|
FP16
97.32 TFLOPS
|
|
Form Factor
PCIe Card
2.1-Slots
|
Form Factor
PCIe Card
2.5-Slots
|
|
TDP
575W
|
TDP
304W
|
|
Power Connectors
-
1x 16-Pin 12VHPWR
|
Power Connectors
2x 8-Pin
-
|
Peak AI Performance
|
|
GeForce RTX 5090 - 3.35 PFLOPS FP4 Tensor Sparse
x2.15
Radeon RX 9070 XT - 1.56 POPS INT4 Tensor Sparse
x1
FP32
|
|
GeForce RTX 5090 - 104.75 TFLOPS FP32
x2.15
Radeon RX 9070 XT - 48.66 TFLOPS FP32
x1
FP16
|
|
GeForce RTX 5090 - 104.75 TFLOPS FP16
x1.08
Radeon RX 9070 XT - 97.32 TFLOPS FP16
x1
|
|
GeForce RTX 5090 - 1792GB/s
x2.87
Radeon RX 9070 XT - 624GB/s
x1
|
|
GeForce RTX 5090 - 575W
x1.89
Radeon RX 9070 XT - 304W
x1
|
GB6 OpenCL 385,770
100%
|
GB6 OpenCL N/A
0%
|
|
0%
|
0%
|
|
GB6 Vulkan 377,445
100%
|
GB6 Vulkan N/A
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
Manufacturer
NVIDIA
|
Manufacturer
AMD
|
|
Chip Designer
NVIDIA
|
Chip Designer
AMD
|
|
Architecture
Blackwell
|
Architecture
RDNA 4
|
|
Family
GeForce 50
|
Family
Radeon RX 9000
|
|
Codename
NV192
GB202
Variant
GB202-300-A1
|
Codename
-
Navi 48
Variant
Navi 48 XT
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
1/6/2025
|
Release Date
1/6/2025
|
|
Foundry
TSMC
|
Foundry
TSMC
|
|
Fabrication Node
4NP
|
Fabrication Node
N4P
|
|
Die Size
762 mm²
|
Die Size
357 mm²
|
|
Transistor Count
92.2 Billion
|
Transistor Count
53.9 Billion
|
|
Transistor Density
121.07M/mm²
|
Transistor Density
151.19M/mm²
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
21760 Shaders
|
Shading Units
4096 Shaders
|
|
Texture Mapping Units
680 TMUs
|
Texture Mapping Units
512 TMUs
|
|
Render Output Units
176 ROPs
|
Render Output Units
128 ROPs
|
|
Tensor Cores
680 T-Cores
|
Tensor Cores
128 T-Cores
|
|
Ray-Tracing Cores
170 RT-Cores
|
Ray-Tracing Cores
64 RT-Cores
|
|
Streaming Multiprocessors
170 SMs
|
-
-
|
|
-
-
|
Compute Units
64 CUs
|
|
Graphics Processing Clusters
11 GPCs
|
-
-
|
|
2010MHz Base
2407MHz
|
2400MHz Base
2970MHz
|
|
Peak AI Performance
3.35 PFLOPS
FP4 Tensor Sparse
|
Peak AI Performance
1.56 POPS
INT4 Tensor Sparse
|
|
FP4
1.68 PFLOPS Tensor
3.35 PFLOPS Tensor Sparse
|
-
-
-
|
|
FP8
-
838.02 TFLOPS Tensor (FP16 Accumulate)
1.68 PFLOPS Tensor (FP16 Accumulate) Sparse
419.01 TFLOPS Tensor (FP32 Accumulate)
838.02 TFLOPS Tensor (FP32 Accumulate) Sparse
|
FP8
194.64 TFLOPS
194.64 TFLOPS Tensor (FP16 Accumulate)
389.28 TFLOPS Tensor (FP16 Accumulate) Sparse
194.64 TFLOPS Tensor (FP32 Accumulate)
389.28 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP16
104.75 TFLOPS
419.01 TFLOPS Tensor (FP16 Accumulate)
838.02 TFLOPS Tensor (FP16 Accumulate) Sparse
209.51 TFLOPS Tensor (FP32 Accumulate)
419.01 TFLOPS Tensor (FP32 Accumulate) Sparse
|
FP16
97.32 TFLOPS
97.32 TFLOPS Tensor (FP16 Accumulate)
194.64 TFLOPS Tensor (FP16 Accumulate) Sparse
97.32 TFLOPS Tensor (FP32 Accumulate)
194.64 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP32
104.75 TFLOPS
|
FP32
48.66 TFLOPS
|
|
FP64
1.64 TFLOPS
|
FP64
1.52 TFLOPS
|
|
BF16
104.75 TFLOPS
209.51 TFLOPS Tensor
419.01 TFLOPS Tensor Sparse
|
BF16
97.32 TFLOPS
97.32 TFLOPS Tensor
194.64 TFLOPS Tensor Sparse
|
|
TF32
104.75 TFLOPS Tensor
209.51 TFLOPS Tensor Sparse
|
-
-
-
|
|
-
-
-
|
INT4
778.57 TOPS Tensor
1.56 POPS Tensor Sparse
|
|
INT8
838.02 TOPS Tensor
1.68 POPS Tensor Sparse
|
INT8
389.28 TOPS Tensor
778.57 TOPS Tensor Sparse
|
|
INT32
104.75 TOPS
|
INT32
24.33 TOPS
|
|
Ray Tracing
317.7 TOPS
|
-
-
|
|
Pixel Fillrate
423.632 GPixel/s
|
Pixel Fillrate
380.16 GPixel/s
|
|
Texture Fillrate
1636.76 GTexel/s
|
Texture Fillrate
1520.64 GTexel/s
|
|
-
-
|
L0
64KB/WGP
|
|
L1
64KB/SM Tex
128KB/SM
-
|
L1
-
-
256KB/Array
|
|
L2
96MB Shared
|
L2
6MB Shared
|
|
-
-
-
|
L3
64MB Shared
2.25TB/s
|
|
32GB
GDDR7
|
16GB
GDDR6
|
|
Bus Width
512Bit
|
Bus Width
256Bit
|
|
Clock
2210MHz
Transfer Rate
28GT/s
Bandwidth
1792GB/s
|
Clock
2438MHz
Transfer Rate
19.5GT/s
Bandwidth
624GB/s
|
|
TDP
575W
|
TDP
304W
|
|
Temp
90°C Max
|
-
-
|
|
3x DisplayPort 2.1
1x HDMI 2.1
|
3x DisplayPort 2.1
1x HDMI 2.1
|
|
Max Resolution
7680x4320
|
Max Resolution
15360x8640
|
|
Max Resolution Refresh Rate
165Hz
|
Max Resolution Refresh Rate
165Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
|
Variable Refresh Rate
-
FreeSync
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
4
|
Multi Monitor Support
3
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.3
|
|
Model
3x NVENC 9
|
Model
VCN 4.0
|
|
Codec
-
AVC (H.264)
HEVC (H.265)
AV1
|
Codec
VP9
AVC (H.264)
HEVC (H.265)
AV1
|
|
Model
2x NVDEC 6
|
Model
VCN 4.0
|
|
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
JPEG
VC-1
-
VP9
AVC (H.264)
HEVC (H.265)
AV1
|
|
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
2.2
Vulkan
1.3
|
|
Shader Model
6.8
CUDA
12.8
-
-
PureVideo HD
VP13
VDPAU
Feature Set M
|
Shader Model
6.8
-
-
GFX
12
-
-
-
-
|
|
2x Fans
|
3x Fans
|
|
Power Connectors
-
1x 16-Pin 12VHPWR
|
Power Connectors
2x 8-Pin
-
|
|
Slots Required
2.1
PCIe Version
5.0
PCIe Lanes
16
|
Slots Required
2.5
PCIe Version
5.0
PCIe Lanes
16
|
|
-
-
-
-
|
Multi GPU Support
Supported
Type
CrossFire XDMA
|
|
Height
137 mm (5.39 in)
Width
304 mm (11.97 in)
Depth
42 mm (1.65 in)
|
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
50 mm (1.97 in)
|
Copy Link