NVIDIA T4 vs NVIDIA GRID RTX T10-16

NVIDIA T4
NVIDIA GRID RTX T10-16
2560 Shaders
16GB GDDR6
1590MHz
4608 Shaders
16GB GDDR6
1065MHz
Peak AI Performance
260.51 TOPS
INT4 Tensor
Peak AI Performance
314.08 TOPS
INT8 Tensor
FP32
8.14 TFLOPS
FP32
9.82 TFLOPS
FP16
16.28 TFLOPS
FP16
19.63 TFLOPS
Form Factor
PCIe Card
1.0-Slots
Form Factor
PCIe Card
2.0-Slots
TDP
70W
TDP
260W
-
-
-
Power Connectors
1x 6-Pin
1x 8-Pin

Peak AI Performance

  • 17% slower vs GRID RTX T10-16
  • 21% faster vs T4
T4 - 260.51 TOPS INT4 Tensor
x1
GRID RTX T10-16 - 314.08 TOPS INT8 Tensor
x1.21

FP32

  • 17% slower vs GRID RTX T10-16
  • 21% faster vs T4
T4 - 8.14 TFLOPS FP32
x1
GRID RTX T10-16 - 9.82 TFLOPS FP32
x1.21

FP16

  • 17% slower vs GRID RTX T10-16
  • 21% faster vs T4
T4 - 16.28 TFLOPS FP16
x1
GRID RTX T10-16 - 19.63 TFLOPS FP16
x1.21
  • 74% slower vs GRID RTX T10-16
  • 3.78x faster vs T4
T4 - 160GB/s
x1
GRID RTX T10-16 - 604.8GB/s
x3.78
  • 73% lower vs GRID RTX T10-16
  • 271% higher vs T4
T4 - 70W
x1
GRID RTX T10-16 - 260W
x3.71
Manufacturer
NVIDIA
Manufacturer
NVIDIA
Chip Designer
NVIDIA
Chip Designer
NVIDIA
Architecture
Turing
Architecture
Turing
Family
Server
Family
GRID
Codename
NV164
TU104
Variant
TU104-895-A1
Codename
NV162
TU102
-
-
Market Segment
Server
Market Segment
Server
Release Date
9/13/2018
Release Date
1/1/2020
Foundry
TSMC
Foundry
TSMC
Fabrication Node
12FFN
Fabrication Node
12FFN
Die Size
545 mm²
Die Size
754 mm²
Transistor Count
13.6 Billion
Transistor Count
18.6 Billion
Transistor Density
24.95M/mm²
Transistor Density
24.67M/mm²
Form
PCIe Card
Form
PCIe Card
Shading Units
2560 Shaders
Shading Units
4608 Shaders
Texture Mapping Units
160 TMUs
Texture Mapping Units
288 TMUs
Render Output Units
64 ROPs
Render Output Units
96 ROPs
Tensor Cores
320 T-Cores
Tensor Cores
576 T-Cores
Ray-Tracing Cores
40 RT-Cores
Ray-Tracing Cores
72 RT-Cores
Streaming Multiprocessors
40 SMs
Streaming Multiprocessors
72 SMs
585MHz Base
1590MHz
-
1065MHz
Peak AI Performance
260.51 TOPS
INT4 Tensor
Peak AI Performance
314.08 TOPS
INT8 Tensor
FP16
16.28 TFLOPS
65.13 TFLOPS Tensor (FP16 Accumulate)
65.13 TFLOPS Tensor (FP32 Accumulate)
FP16
19.63 TFLOPS
-
78.52 TFLOPS Tensor (FP32 Accumulate)
FP32
8.14 TFLOPS
-
FP32
9.82 TFLOPS
78.52 TFLOPS Tensor
FP64
250 GFLOPS
-
FP64
310 GFLOPS
78.52 TFLOPS Tensor
-
-
BF16
157.04 TFLOPS Tensor
INT4
260.51 TOPS Tensor
-
-
INT8
130.25 TOPS Tensor
INT8
314.08 TOPS Tensor
Ray Tracing
31.8 TOPS
Ray Tracing
38.3 TOPS
Pixel Fillrate
101.76 GPixel/s
Pixel Fillrate
102.24 GPixel/s
Texture Fillrate
254.4 GTexel/s
Texture Fillrate
306.72 GTexel/s
L1
32KB/SM Tex
64KB/SM
L1
32KB/SM Tex
64KB/SM
L2
4MB Shared
L2
6MB Shared
16GB
GDDR6
16GB
GDDR6
Bus Width
256Bit
Bus Width
384Bit
Clock
625MHz
Transfer Rate
5GT/s
Bandwidth
160GB/s
Clock
1575MHz
Transfer Rate
12.6GT/s
Bandwidth
604.8GB/s
TDP
70W
TDP
260W
Max Resolution
Unknown
Max Resolution
Unknown
Variable Refresh Rate
G-Sync
FreeSync
Variable Refresh Rate
G-Sync
FreeSync
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
Unknown
Model
NVENC 7
Model
NVENC 7
Codec
AVC (H.264)
HEVC (H.265)
Codec
AVC (H.264)
HEVC (H.265)
Model
NVDEC 4
Model
NVDEC 4
Codec
MPEG-1
MPEG-2
MPEG-4
VC-1
VP8
VP9
AVC (H.264)
HEVC (H.265)
Codec
MPEG-1
MPEG-2
MPEG-4
VC-1
VP8
VP9
AVC (H.264)
HEVC (H.265)
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
7.5
PureVideo HD
VP10
VDPAU
Feature Set J
Shader Model
6.6
CUDA
7.5
PureVideo HD
VP10
VDPAU
Feature Set J
-
-
-
Power Connectors
1x 6-Pin
1x 8-Pin
Slots Required
1.0
PCIe Version
3.0
PCIe Lanes
16
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
NVLink
-
-
-
-
Height
69 mm (2.72 in)
Width
168 mm (6.61 in)
Depth
20 mm (0.79 in)
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
40 mm (1.57 in)
Change Comparison