NVIDIA Tesla K8 vs NVIDIA GeForce RTX 4070 SUPER
GPU Specs Compare
Graphics Card
Release Date
Sep 2014
Jan 2024
Generation
Tesla
GeForce 40
Type
Professional
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
693 MHz
1980 MHz
Boost Clock
811 MHz
2475 MHz
Memory Clock
1250 MHz
1313 MHz
Memory
Memory Size
8GB
12GB
Memory Type
GDDR5
GDDR6X
Memory Bus
256bit
192bit
Bandwidth
160.0GB/s
504.2GB/s
Render Config
Shading Units
1536
7168
TMUs
128
224
ROPs
32
80
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
512 KB
48 MB
SM Count
-
56
Tensor Cores
-
224
RT Cores
-
56
Theoretical Performance
Pixel Rate
25.95 GPixel/s
198.0 GPixel/s
Texture Rate
103.8 GTexel/s
554.4 GTexel/s
FP32 (float)
2.491 TFLOPS
35.48 TFLOPS
FP64 (double)
103.8 GFLOPS
554.4 GFLOPS
FP16 (half)
-
35.48 TFLOPS
Graphics Processor
GPU Name
GK104
AD104
Architecture
Kepler
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
28 nm
5 nm
Transistors
3.54 billion
35.8 billion
Die Size
294 mm²
294 mm²
GPU Variant
-
AD104-350-A1
Board Design
TDP
100W
220W
Suggested PSU
300 W
550 W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 6-pin
1x 16-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
1.3
CUDA
3.0
8.9
Shader Model
5.1
6.8