NVIDIA H100 Specs

NVIDIA H100
14592 Shaders
80GB HBM2e
1755MHz
Peak Performance
3.03 POPS
INT8 Tensor Sparse
FP32
51.22 TFLOPS
FP16
102.44 TFLOPS
Form Factor
PCIe Card
2.0-Slots
TDP
350W
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
GB6 Metal N/A
0%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT Metal N/A
0%
Manufacturer
NVIDIA
Chip Designer
NVIDIA
Architecture
Hopper
Family
Server
Codename
NV180
GH100
-
-
Market Segment
Server
Release Date
3/22/2022
Foundry
TSMC
-
Fabrication Node
4N
-
Die Size
814 mm²
-
Transistor Count
80 Billion
-
Transistor Density
98.28M/mm²
-
Form
PCIe Card
Shading Units
14592 Shaders
-
Texture Mapping Units
456 TMUs
Render Output Units
24 ROPs
Tensor Cores
456 T-Cores
-
-
Streaming Multiprocessors
114 SMs
-
-
-
-
-
-
1620MHz Tensor
-
1065MHz Base
1755MHz
Peak Performance
3.03 POPS
INT8 Tensor Sparse
-
-
-
FP8
-
1.51 PFLOPS Tensor (FP16 Accumulate)
3.03 PFLOPS Tensor (FP16 Accumulate) Sparse
1.51 PFLOPS Tensor (FP32 Accumulate)
3.03 PFLOPS Tensor (FP32 Accumulate) Sparse
FP16
102.44 TFLOPS
756.45 TFLOPS Tensor (FP16 Accumulate)
1.51 PFLOPS Tensor (FP16 Accumulate) Sparse
756.45 TFLOPS Tensor (FP32 Accumulate)
1.51 PFLOPS Tensor (FP32 Accumulate) Sparse
FP32
51.22 TFLOPS
-
-
FP64
25.61 TFLOPS
47.28 TFLOPS Tensor
BF16
102.44 TFLOPS
756.45 TFLOPS Tensor
1.51 PFLOPS Tensor Sparse
TF32
378.23 TFLOPS Tensor
756.45 TFLOPS Tensor Sparse
-
-
-
INT8
-
1.51 POPS Tensor
3.03 POPS Tensor Sparse
INT32
25.61 TOPS
-
-
Pixel Fillrate
42.12 GPixel/s
-
-
Texture Fillrate
800.28 GTexel/s
-
-
L1
64KB/SM Tex
256KB/SM
-
-
L2
50MB Shared
-
-
-
80GB
HBM2e
-
Bus Width
5120Bit
Clock
1593MHz
Transfer Rate
3.2GT/s
Bandwidth
2039GB/s
-
-
-
-
-
-
-
-
-
TDP
350W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Variable Refresh Rate
G-Sync
FreeSync
-
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
-
-
No Encoders
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Decoders
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
OpenCL
3.0
-
-
-
-
CUDA
9.0
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
-
-
-
-
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
Slots Required
2.0
PCIe Version
5.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
NVLink
Height
111 mm (4.37 in)
Width
268 mm (10.55 in)
Depth
40 mm (1.57 in)
Change Comparison