GPU Comparison

NVIDIA
GEFORCE

NVIDIA B200

CORE STATE GB100
VRAM 90 GB
CLOCK SPEED 1965 MHz
TDP 1000 W
BUS WIDTH 4096 bit
ARCHITECTURE Blackwell
nm
PROCESS 5 nm
LAUNCH DATE
VS
NVIDIA
GEFORCE

T400 4 GB

CORE STATE TU117
VRAM 4 GB
CLOCK SPEED 1425 MHz
TDP 30 W
BUS WIDTH 64 bit
ARCHITECTURE Turing
nm
PROCESS 12 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

geekbench_opencl
345,482
17,320
geekbench_vulkan
N/A
16,263

DETAILED SPECIFICATIONS

SPECIFICATION
B200
T400 4 GB
Core Specs
Shading Units
18,944
384 -98.0%
Shaders
18,944
384 -98.0%
TMUs
592
24 -95.9%
ROPs
24
16 -33.3%
SM Count
148
6 -95.9%
Clocks
Base Clock
700 MHz
420 MHz
Boost Clock
1965 MHz
1425 MHz
Memory Clock
2000 MHz 8 Gbps effective
1250 MHz 10 Gbps effective
Memory
Memory Size
90 GB
4 GB
VRAM (MB)
92,160
4,096 -95.6%
Memory Type
HBM3e
GDDR6
Memory Bus
4096 bit
64 bit
Bandwidth
4.10 TB/s
80.00 GB/s
Cache
L1 Cache
256 KB (per SM)
64 KB (per SM)
L2 Cache
50 MB
1024 KB
Performance
Pixel Rate
47.16 GPixel/s
22.80 GPixel/s
Texture Rate
1,163.3 GTexel/s
34.20 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
1,094.4 GFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
34.20 GFLOPS (1:32)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
2.189 TFLOPS (2:1)
AI/RT
Tensor Cores
592
Power
TDP
1000 W
30 W
TDP (W)
1,000
30 -97.0%
Suggested PSU
1400 W
200 W
Power Connectors
None
Architecture
Architecture
Blackwell
Turing
GPU Name
GB100
TU117
Generation
Server Blackwell (Bxx)
Quadro Turing (Tx000)
Process Size
5 nm
12 nm
Transistors
104,000 million
4,700 million
Die Size
200 mm²
Foundry
TSMC
TSMC
Density
23.5M / mm²
API Support
DirectX
12 (12_1)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
10.0
7.5
Shader Model
6.8
Physical
Slot Width
SXM Module
Single-slot
Outputs
No outputs
3x mini-DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Hopper
Quadro Volta
Successor
Server Rubin
Workstation Ampere
View B200 Details View T400 4 GB Details