NVIDIA GeForce GTX 780 Ti Engineering Sample vs NVIDIA B100
We compared two Desktop platform GPUs: 3GB VRAM GeForce GTX 780 Ti Engineering Sample and 96GB VRAM B100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 780 Ti Engineering Sample 's Advantages
Lower TDP (250W vs 1000W)
NVIDIA B100 's Advantages
Boost Clock has increased by 98% (1837MHz vs 928MHz)
More VRAM (96GB vs 3GB)
Larger VRAM bandwidth (4.10TB/s vs 336.6GB/s)
14016 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 780 Ti Engineering Sample
5.345 TFLOPS
B100
+1061%
62.08 TFLOPS
Graphics Card
Unknown
Release Date
Nov 2024
GeForce 700
Generation
Server Blackwell
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
875 MHz
Base Clock
1665 MHz
928 MHz
Boost Clock
1837 MHz
1753 MHz
Memory Clock
2000 MHz
Memory
3GB
Memory Size
96GB
GDDR5
Memory Type
HBM3e
384bit
Memory Bus
4096bit
336.6GB/s
Bandwidth
4.10TB/s
Render Config
-
-
-
-
SM Count
132
2880
Shading Units
16896
240
TMUs
528
48
ROPs
24
-
Tensor Cores
528
-
-
-
16 KB (per SMX)
L1 Cache
256 KB (per SM)
1536 KB
L2 Cache
50 MB
-
-
-
Theoretical Performance
55.68 GPixel/s
Pixel Rate
44.09 GPixel/s
222.7 GTexel/s
Texture Rate
969.9 GTexel/s
-
FP16 (half)
248.3 TFLOPS
5.345 TFLOPS
FP32 (float)
62.08 TFLOPS
222.7 GFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
250W
TDP
1000W
600 W
Suggested PSU
1400 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
GK180
GPU Name
GB102
GK180-425-A1
GPU Variant
-
Kepler
Architecture
Blackwell
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
7.08 billion
Transistors
104 billion
561 mm²
Die Size
Unknown
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.2.175
Vulkan
N/A
3.5
CUDA
10.1
5.1
Shader Model
N/A
