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
Tesla K20Xm
CORE STATE
GK110
VRAM
6 GB
CLOCK SPEED
—
TDP
235 W
BUS WIDTH
384 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2012
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
H200 NVL
Tesla K20Xm
Core Specs
Shading Units
16,896
2,688
-84.1%
Shaders
16,896
2,688
-84.1%
TMUs
528
224
-57.6%
ROPs
24
48
+100.0%
SM Count
132
—
Clocks
Base Clock
1365 MHz
—
Boost Clock
1785 MHz
—
GPU Clock
—
732 MHz
Memory Clock
1593 MHz
6.4 Gbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
141 GB
6 GB
VRAM (MB)
144,384
6,144
-95.7%
Memory Type
HBM3e
GDDR5
Memory Bus
6144 bit
384 bit
Bandwidth
4.89 TB/s
249.6 GB/s
Cache
L1 Cache
256 KB (per SM)
16 KB (per SMX)
L2 Cache
50 MB
1536 KB
Performance
Pixel Rate
42.84 GPixel/s
40.99 GPixel/s
Texture Rate
942.5 GTexel/s
164.0 GTexel/s
FP32 (TFLOPS)
60.32 TFLOPS
3.935 TFLOPS
FP64 (TFLOPS)
30.16 TFLOPS (1:2)
1,311.7 GFLOPS (1:3)
FP16 (TFLOPS)
241.3 TFLOPS (4:1)
—
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
—
Architecture
Architecture
Hopper
Kepler
GPU Name
GH100
GK110
Generation
Server Hopper
(Hxx)
Tesla Kepler
(Kxx)
Process Size
5 nm
28 nm
Transistors
80,000 million
7,080 million
Die Size
814 mm²
561 mm²
Foundry
TSMC
TSMC
Density
98.3M / mm²
12.6M / mm²
API Support
DirectX
—
12 (11_0)
OpenGL
—
4.6
Vulkan
—
1.2.175
OpenCL
3.0
3.0
CUDA
9.0
3.5
Shader Model
—
6.5 (5.1)
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
111 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Launch Price
—
7,699 USD
Production
Active
End-of-life
Predecessor
Server Ada
Tesla Fermi
Successor
Server Blackwell
Tesla Maxwell