GPU Comparison
GEFORCE
NVIDIA GeForce GTX 950A
CORE STATE
GM107
VRAM
2 GB
CLOCK SPEED
1124 MHz
TDP
75 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell
PROCESS
28 nm
LAUNCH DATE
2015
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
DETAILED SPECIFICATIONS
SPECIFICATION
GTX 950A
H200 NVL
Core Specs
Shading Units
640
16,896
+2540.0%
Shaders
640
16,896
+2540.0%
TMUs
40
528
+1220.0%
ROPs
16
24
+50.0%
SM Count
—
132
Clocks
Base Clock
993 MHz
1365 MHz
Boost Clock
1124 MHz
1785 MHz
Memory Clock
1001 MHz
2 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
2 GB
141 GB
VRAM (MB)
2,048
144,384
+6950.0%
Memory Type
DDR3
HBM3e
Memory Bus
128 bit
6144 bit
Bandwidth
32.03 GB/s
4.89 TB/s
Cache
L1 Cache
64 KB (per SMM)
256 KB (per SM)
L2 Cache
2 MB
50 MB
Performance
Pixel Rate
17.98 GPixel/s
42.84 GPixel/s
Texture Rate
44.96 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
1,438.7 GFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
44.96 GFLOPS (1:32)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
—
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
—
528
Power
TDP
75 W
600 W
TDP (W)
75
600
+700.0%
Suggested PSU
—
1000 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
Maxwell
Hopper
GPU Name
GM107
GH100
Generation
GeForce 900A
Server Hopper
(Hxx)
Process Size
28 nm
5 nm
Transistors
1,870 million
80,000 million
Die Size
148 mm²
814 mm²
Foundry
TSMC
TSMC
Density
12.6M / mm²
98.3M / mm²
API Support
DirectX
12 (11_0)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
5.0
9.0
Shader Model
6.7 (5.1)
—
Physical
Slot Width
MXM Module
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
MXM-B (3.0)
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
GeForce 800A
Server Ada
Successor
—
Server Blackwell