Home GPU Comparison NVIDIA B200 SXM 192 GB vs NVIDIA T400 4 GB

NVIDIA B200 SXM 192 GB vs NVIDIA T400 4 GB

We compared two Desktop platform GPUs: 192GB VRAM B200 SXM 192 GB and 4GB VRAM T400 4 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA B200 SXM 192 GB 's Advantages
Released 2 years and 8 months late
Boost Clock has increased by 29% (1837MHz vs 1425MHz)
More VRAM (192GB vs 4GB)
Larger VRAM bandwidth (4100GB/s vs 80.00GB/s)
16512 additional rendering cores
NVIDIA T400 4 GB 's Advantages
Lower TDP (30W vs 1000W)

Score

Benchmark

FP32 (float)
B200 SXM 192 GB +5574%
62.08 TFLOPS
T400 4 GB
1.094 TFLOPS
VS

Graphics Card

Jan 2024
Release Date
May 2021
Tesla Blackwell
Generation
Quadro
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16

Clock Speeds

1665 MHz
Base Clock
420 MHz
1837 MHz
Boost Clock
1425 MHz
2000 MHz
Memory Clock
1250 MHz

Memory

192GB
Memory Size
4GB
HBM3e
Memory Type
GDDR6
4096bit
Memory Bus
64bit
4100GB/s
Bandwidth
80.00GB/s

Render Config

-
-
-
132
SM Count
6
16896
Shading Units
384
528
TMUs
24
24
ROPs
16
528
Tensor Cores
-
-
-
-
256 KB (per SM)
L1 Cache
64 KB (per SM)
50 MB
L2 Cache
1024 KB
-
-
-

Theoretical Performance

44.09 GPixel/s
Pixel Rate
22.80 GPixel/s
969.9 GTexel/s
Texture Rate
34.20 GTexel/s
248.3 TFLOPS
FP16 (half)
2.189 TFLOPS
62.08 TFLOPS
FP32 (float)
1094 GFLOPS
31.04 TFLOPS
FP64 (double)
34.20 GFLOPS

Board Design

1000W
TDP
30W
1400 W
Suggested PSU
200 W
No outputs
Outputs
3x mini-DisplayPort 1.4a
-
Power Connectors
None

Graphics Processor

GB100
GPU Name
TU117
-
-
-
Blackwell
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
208 billion
Transistors
4.7 billion
Unknown
Die Size
200 mm²

Graphics Features

N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
9.0
CUDA
7.5
N/A
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy