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 M4
CORE STATE
GM206
VRAM
4 GB
CLOCK SPEED
1072 MHz
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
H200 NVL
Tesla M4
Core Specs
Shading Units
16,896
1,024
-93.9%
Shaders
16,896
1,024
-93.9%
TMUs
528
64
-87.9%
ROPs
24
32
+33.3%
SM Count
132
—
Clocks
Base Clock
1365 MHz
872 MHz
Boost Clock
1785 MHz
1072 MHz
Memory Clock
1593 MHz
6.4 Gbps effective
1375 MHz
5.5 Gbps effective
Memory
Memory Size
141 GB
4 GB
VRAM (MB)
144,384
4,096
-97.2%
Memory Type
HBM3e
GDDR5
Memory Bus
6144 bit
128 bit
Bandwidth
4.89 TB/s
88.00 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SMM)
L2 Cache
50 MB
1024 KB
Performance
Pixel Rate
42.84 GPixel/s
34.30 GPixel/s
Texture Rate
942.5 GTexel/s
68.61 GTexel/s
FP32 (TFLOPS)
60.32 TFLOPS
2.195 TFLOPS
FP64 (TFLOPS)
30.16 TFLOPS (1:2)
68.61 GFLOPS (1:32)
FP16 (TFLOPS)
241.3 TFLOPS (4:1)
—
AI/RT
Tensor Cores
528
—
Power
TDP
600 W
50 W
TDP (W)
600
50
-91.7%
Suggested PSU
1000 W
250 W
Power Connectors
8-pin EPS
—
Architecture
Architecture
Hopper
Maxwell 2.0
GPU Name
GH100
GM206
Generation
Server Hopper
(Hxx)
Tesla Maxwell
(Mxx)
Process Size
5 nm
28 nm
Transistors
80,000 million
2,940 million
Die Size
814 mm²
228 mm²
Foundry
TSMC
TSMC
Density
98.3M / mm²
12.9M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
9.0
5.2
Shader Model
—
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
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
Production
Active
End-of-life
Predecessor
Server Ada
Tesla Kepler
Successor
Server Blackwell
Tesla Pascal