NVIDIA GeForce GTX 970 vs NVIDIA H200 NVL
We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 970 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 970 's Advantages
Lower TDP (148W vs 600W)
NVIDIA H200 NVL 's Advantages
Released 10 years and 2 months late
Boost Clock has increased by 52% (1785MHz vs 1178MHz)
More VRAM (141GB vs 4GB)
Larger VRAM bandwidth (4.89TB/s vs 224.4GB/s)
15232 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 970
3.92 TFLOPS
H200 NVL
+1438%
60.32 TFLOPS
Graphics Card
Sep 2014
Release Date
Nov 2024
GeForce 900
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1050 MHz
Base Clock
1365 MHz
1178 MHz
Boost Clock
1785 MHz
1753 MHz
Memory Clock
1593 MHz
Memory
4GB
Memory Size
141GB
GDDR5
Memory Type
HBM3e
256bit
Memory Bus
6144bit
224.4GB/s
Bandwidth
4.89TB/s
Render Config
-
-
-
-
SM Count
132
1664
Shading Units
16896
104
TMUs
528
56
ROPs
24
-
Tensor Cores
528
-
-
-
48 KB (per SMM)
L1 Cache
256 KB (per SM)
2 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
65.97 GPixel/s
Pixel Rate
42.84 GPixel/s
122.5 GTexel/s
Texture Rate
942.5 GTexel/s
-
FP16 (half)
241.3 TFLOPS
3.920 TFLOPS
FP32 (float)
60.32 TFLOPS
122.5 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
148W
TDP
600W
300 W
Suggested PSU
1000 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
No outputs
2x 6-pin
Power Connectors
8-pin EPS
Graphics Processor
GM204
GPU Name
GH100
GM204-200-A1
GPU Variant
-
Maxwell 2.0
Architecture
Hopper
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
5.2 billion
Transistors
80 billion
398 mm²
Die Size
814 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
5.2
CUDA
9.0
6.4
Shader Model
N/A
