GPU Comparison
GEFORCE
NVIDIA H200 NVL
CORE STATE
GH100
VRAM
141 GB
CLOCK SPEED
1785 MHz
TDP
600 W
BUS WIDTH
6144 bit
ARCHITECTURE
Hopper
PROCESS
5 nm
LAUNCH DATE
2024
VS
GEFORCE
Quadro GP100
CORE STATE
GP100
VRAM
16 GB
CLOCK SPEED
1443 MHz
TDP
235 W
BUS WIDTH
4096 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
H200 NVL
Quadro GP100
Core Specs
Shading Units
16,896
3,584
-78.8%
Shaders
16,896
3,584
-78.8%
TMUs
528
224
-57.6%
ROPs
24
96
+300.0%
SM Count
132
56
-57.6%
Clocks
Base Clock
1365 MHz
1304 MHz
Boost Clock
1785 MHz
1443 MHz
Memory Clock
1593 MHz
6.4 Gbps effective
715 MHz
1430 Mbps effective
Memory
Memory Size
141 GB
16 GB
VRAM (MB)
144,384
16,384
-88.7%
Memory Type
HBM3e
HBM2
Memory Bus
6144 bit
4096 bit
Bandwidth
4.89 TB/s
732.2 GB/s
Cache
L1 Cache
256 KB (per SM)
24 KB (per SM)
L2 Cache
50 MB
4 MB
Performance
Pixel Rate
42.84 GPixel/s
138.5 GPixel/s
Texture Rate
942.5 GTexel/s
323.2 GTexel/s
FP32 (TFLOPS)
60.32 TFLOPS
10.34 TFLOPS
FP64 (TFLOPS)
30.16 TFLOPS (1:2)
5.172 TFLOPS (1:2)
FP16 (TFLOPS)
241.3 TFLOPS (4:1)
20.69 TFLOPS (2:1)
AI/RT
Tensor Cores
528
—
Power
TDP
600 W
235 W
TDP (W)
600
235
-60.8%
Suggested PSU
1000 W
550 W
Power Connectors
8-pin EPS
1x 8-pin
Architecture
Architecture
Hopper
Pascal
GPU Name
GH100
GP100
Generation
Server Hopper
(Hxx)
Quadro Pascal
(Px000)
Process Size
5 nm
16 nm
Transistors
80,000 million
15,300 million
Die Size
814 mm²
610 mm²
Foundry
TSMC
TSMC
Density
98.3M / mm²
25.1M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.3
OpenCL
3.0
3.0
CUDA
9.0
6.0
Shader Model
—
6.0
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
111 mm
4.4 inches
111 mm
4.4 inches
Outputs
No outputs
1x DVI4x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Ada
Quadro Maxwell
Successor
Server Blackwell
Quadro Volta