ASUS 4x GeForce RTX 3090 Turbo vs EVGA GeForce RTX 3090 FTW3 ULTRA
ASUS 4x GeForce RTX 3090 Turbo
EVGA GeForce RTX 3090 FTW3 ULTRA
$1,000
|
4x 10496 Shaders
96GB (4x 24GB) GDDR6X
1695MHz
|
10496 Shaders
24GB GDDR6X
1800MHz
|
|
Peak AI Performance
4.55 POPS
INT4 Tensor Sparse
|
Peak AI Performance
1.21 POPS
INT4 Tensor Sparse
|
|
FP32
142.32 TFLOPS
|
FP32
37.79 TFLOPS
|
|
FP16
142.32 TFLOPS
|
FP16
37.79 TFLOPS
|
|
Form Factor
PCIe Card
4x 2.7-Slots
|
Form Factor
PCIe Card
2.8-Slots
|
|
TDP
1400W
|
TDP
350W
|
|
Power Connectors
2x 8-Pin
|
Power Connectors
3x 8-Pin
|
Peak AI Performance
|
|
4x GeForce RTX 3090 Turbo - 4.55 POPS INT4 Tensor Sparse
x3.76
GeForce RTX 3090 FTW3 ULTRA - 1.21 POPS INT4 Tensor Sparse
x1
FP32
|
|
4x GeForce RTX 3090 Turbo - 142.32 TFLOPS FP32
x3.77
GeForce RTX 3090 FTW3 ULTRA - 37.79 TFLOPS FP32
x1
FP16
|
|
4x GeForce RTX 3090 Turbo - 142.32 TFLOPS FP16
x3.77
GeForce RTX 3090 FTW3 ULTRA - 37.79 TFLOPS FP16
x1
|
|
4x GeForce RTX 3090 Turbo - 936GB/s
x1
GeForce RTX 3090 FTW3 ULTRA - 936GB/s
x1
|
|
4x GeForce RTX 3090 Turbo - 1400W
x4
GeForce RTX 3090 FTW3 ULTRA - 350W
x1
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
GB5 OpenCL 205,435
67%
|
GB5 OpenCL 218,165
71%
|
|
GB5 CUDA 238,680
67%
|
GB5 CUDA 253,465
71%
|
|
0%
|
0%
|
|
GB5 Vulkan 138,205
67%
|
GB5 Vulkan 146,765
71%
|
|
OCT 2020.1 2,620
345%
|
OCT 2020.1 695
92%
|
|
0%
|
0%
|
|
Manufacturer
ASUS
|
Manufacturer
EVGA
|
|
Chip Designer
NVIDIA
|
Chip Designer
NVIDIA
|
|
Architecture
Ampere
|
Architecture
Ampere
|
|
Family
GeForce 30
|
Family
GeForce 30
|
|
Codename
NV172
GA102
Variant
GA102-300-A1
|
Codename
NV172
GA102
Variant
GA102-300-A1
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
9/24/2020
|
Release Date
9/24/2020
|
|
Foundry
Samsung
|
Foundry
Samsung
|
|
Fabrication Node
8N
|
Fabrication Node
8N
|
|
Die Size
4x 628 mm²
|
Die Size
628 mm²
|
|
Transistor Count
4x 28.3 Billion
|
Transistor Count
28.3 Billion
|
|
Transistor Density
45.04M/mm²
|
Transistor Density
45.04M/mm²
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
4x 10496 Shaders
|
Shading Units
10496 Shaders
|
|
Texture Mapping Units
4x 328 TMUs
|
Texture Mapping Units
328 TMUs
|
|
Render Output Units
4x 112 ROPs
|
Render Output Units
112 ROPs
|
|
Tensor Cores
4x 328 T-Cores
|
Tensor Cores
328 T-Cores
|
|
Ray-Tracing Cores
4x 82 RT-Cores
|
Ray-Tracing Cores
82 RT-Cores
|
|
Streaming Multiprocessors
4x 82 SMs
|
Streaming Multiprocessors
82 SMs
|
|
Graphics Processing Clusters
4x 7 GPCs
|
Graphics Processing Clusters
7 GPCs
|
|
1395MHz Base
1695MHz
|
1395MHz Base
1800MHz
|
|
Peak AI Performance
4.55 POPS
INT4 Tensor Sparse
|
Peak AI Performance
1.21 POPS
INT4 Tensor Sparse
|
|
FP16
142.32 TFLOPS
569.3 TFLOPS Tensor (FP16 Accumulate)
1.14 PFLOPS Tensor (FP16 Accumulate) Sparse
284.65 TFLOPS Tensor (FP32 Accumulate)
569.3 TFLOPS Tensor (FP32 Accumulate) Sparse
|
FP16
37.79 TFLOPS
151.14 TFLOPS Tensor (FP16 Accumulate)
302.28 TFLOPS Tensor (FP16 Accumulate) Sparse
75.57 TFLOPS Tensor (FP32 Accumulate)
151.14 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP32
142.32 TFLOPS
|
FP32
37.79 TFLOPS
|
|
FP64
2.22 TFLOPS
|
FP64
590 GFLOPS
|
|
BF16
142.32 TFLOPS
284.65 TFLOPS Tensor
569.3 TFLOPS Tensor Sparse
|
BF16
37.79 TFLOPS
75.57 TFLOPS Tensor
151.14 TFLOPS Tensor Sparse
|
|
TF32
142.32 TFLOPS Tensor
284.65 TFLOPS Tensor Sparse
|
TF32
37.79 TFLOPS Tensor
75.57 TFLOPS Tensor Sparse
|
|
INT4
2.28 POPS Tensor
4.55 POPS Tensor Sparse
|
INT4
604.57 TOPS Tensor
1.21 POPS Tensor Sparse
|
|
INT8
1.14 POPS Tensor
2.28 POPS Tensor Sparse
|
INT8
302.29 TOPS Tensor
604.57 TOPS Tensor Sparse
|
|
INT32
71.16 TOPS
|
INT32
18.89 TOPS
|
|
Ray Tracing
69.5 TOPS
|
Ray Tracing
73.8 TOPS
|
|
Pixel Fillrate
189.84 GPixel/s
|
Pixel Fillrate
201.6 GPixel/s
|
|
Texture Fillrate
555.96 GTexel/s
|
Texture Fillrate
590.4 GTexel/s
|
|
L1
64KB/SM Tex
128KB/SM
|
L1
64KB/SM Tex
128KB/SM
|
|
L2
6MB Shared
|
L2
6MB Shared
|
|
96GB (4x 24GB)
GDDR6X
|
24GB
GDDR6X
|
|
Bus Width
384Bit
|
Bus Width
384Bit
|
|
Clock
1219MHz
Transfer Rate
19.5GT/s
Bandwidth
936GB/s
|
Clock
1219MHz
Transfer Rate
19.5GT/s
Bandwidth
936GB/s
|
|
TDP
1400W
|
TDP
350W
|
|
Temp
93°C Max
|
Temp
93°C Max
|
|
12x DisplayPort 1.4
4x HDMI 2.1
|
3x DisplayPort 1.4
1x HDMI 2.1
|
|
Max Resolution
7680x4320
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
60Hz
|
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 2.3
|
|
Model
NVENC 7
|
Model
NVENC 7
|
|
Codec
AVC (H.264)
HEVC (H.265)
|
Codec
AVC (H.264)
HEVC (H.265)
|
|
Model
NVDEC 5
|
Model
NVDEC 5
|
|
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)
AV1
|
|
Direct X
12
Direct 3D
12_2
|
Direct X
12
Direct 3D
12_2
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.6
CUDA
8.6
PureVideo HD
VP11
VDPAU
Feature Set K
|
Shader Model
6.6
CUDA
8.6
PureVideo HD
VP11
VDPAU
Feature Set K
|
|
1x Fan
|
3x Fans
|
|
Power Connectors
2x 8-Pin
|
Power Connectors
3x 8-Pin
|
|
Slots Required
2.7
PCIe Version
4.0
PCIe Lanes
16
|
Slots Required
2.8
PCIe Version
4.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
2-way NVLink
|
Multi GPU Support
Supported
Type
2-way NVLink
|
|
Height
138 mm (5.43 in)
Width
313 mm (12.32 in)
Depth
55 mm (2.17 in)
|
Height
136.8 mm (5.39 in)
Width
300 mm (11.81 in)
Depth
56.4 mm (2.22 in)
|
Copy Link