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 P400
CORE STATE
GP107
VRAM
2 GB
CLOCK SPEED
1252 MHz
TDP
30 W
BUS WIDTH
64 bit
ARCHITECTURE
Pascal
PROCESS
14 nm
LAUNCH DATE
2017
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
H200 NVL
Quadro P400
Core Specs
Shading Units
16,896
256
-98.5%
Shaders
16,896
256
-98.5%
TMUs
528
16
-97.0%
ROPs
24
16
-33.3%
SM Count
132
2
-98.5%
Clocks
Base Clock
1365 MHz
1228 MHz
Boost Clock
1785 MHz
1252 MHz
Memory Clock
1593 MHz
6.4 Gbps effective
1002 MHz
4 Gbps effective
Memory
Memory Size
141 GB
2 GB
VRAM (MB)
144,384
2,048
-98.6%
Memory Type
HBM3e
GDDR5
Memory Bus
6144 bit
64 bit
Bandwidth
4.89 TB/s
32.06 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SM)
L2 Cache
50 MB
512 KB
Performance
Pixel Rate
42.84 GPixel/s
20.03 GPixel/s
Texture Rate
942.5 GTexel/s
20.03 GTexel/s
FP32 (TFLOPS)
60.32 TFLOPS
641.0 GFLOPS
FP64 (TFLOPS)
30.16 TFLOPS (1:2)
20.03 GFLOPS (1:32)
FP16 (TFLOPS)
241.3 TFLOPS (4:1)
10.02 GFLOPS (1:64)
AI/RT
Tensor Cores
528
—
Power
TDP
600 W
30 W
TDP (W)
600
30
-95.0%
Suggested PSU
1000 W
200 W
Power Connectors
8-pin EPS
None
Architecture
Architecture
Hopper
Pascal
GPU Name
GH100
GP107
Generation
Server Hopper
(Hxx)
Quadro Pascal
(Px000)
Process Size
5 nm
14 nm
Transistors
80,000 million
3,300 million
Die Size
814 mm²
132 mm²
Foundry
TSMC
Samsung
Density
98.3M / mm²
25.0M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
9.0
6.1
Shader Model
—
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
150 mm
5.9 inches
Height
111 mm
4.4 inches
69 mm
2.7 inches
Outputs
No outputs
3x mini-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