GPU Comparison
GEFORCE
NVIDIA CMP 70HX
CORE STATE
GA104
VRAM
8 GB
CLOCK SPEED
1395 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 70HX
H200 NVL
Core Specs
Shading Units
3,840
16,896
+340.0%
Shaders
3,840
16,896
+340.0%
TMUs
120
528
+340.0%
ROPs
64
24
-62.5%
SM Count
30
132
+340.0%
Clocks
Base Clock
1365 MHz
1365 MHz
Boost Clock
1395 MHz
1785 MHz
Memory Clock
1188 MHz
19 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
8 GB
141 GB
VRAM (MB)
8,192
144,384
+1662.5%
Memory Type
GDDR6X
HBM3e
Memory Bus
256 bit
6144 bit
Bandwidth
608.3 GB/s
4.89 TB/s
Cache
L1 Cache
128 KB (per SM)
256 KB (per SM)
L2 Cache
4 MB
50 MB
Performance
Pixel Rate
89.28 GPixel/s
42.84 GPixel/s
Texture Rate
167.4 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
10.71 TFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
167.4 GFLOPS (1:64)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
10.71 TFLOPS (1:1)
241.3 TFLOPS (4:1)
AI/RT
RT Cores
30
—
Tensor Cores
120
528
+340.0%
Power
TDP
—
600 W
TDP (W)
—
600
Suggested PSU
200 W
1000 W
Power Connectors
1x 12-pin
8-pin EPS
Architecture
Architecture
Ampere
Hopper
GPU Name
GA104
GH100
Generation
Mining GPUs
Server Hopper
(Hxx)
Process Size
8 nm
5 nm
Transistors
17,400 million
80,000 million
Die Size
392 mm²
814 mm²
Foundry
Samsung
TSMC
Density
44.4M / mm²
98.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
8.6
9.0
Shader Model
6.8
—
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
112 mm
4.4 inches
111 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Server Ada
Successor
—
Server Blackwell