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

Quadro K4000

CORE STATE GK106
VRAM 3 GB
CLOCK SPEED
TDP 80 W
BUS WIDTH 192 bit
ARCHITECTURE Kepler
nm
PROCESS 28 nm
LAUNCH DATE 2013

PERFORMANCE BENCHMARKS

geekbench_opencl
345,482
6,816
geekbench_metal
N/A
4,166
geekbench_vulkan
N/A
6,964

DETAILED SPECIFICATIONS

SPECIFICATION
B200
Quadro K4000
Core Specs
Shading Units
18,944
768 -95.9%
Shaders
18,944
768 -95.9%
TMUs
592
64 -89.2%
ROPs
24
24 0.0%
SM Count
148
Clocks
Base Clock
700 MHz
Boost Clock
1965 MHz
GPU Clock
810 MHz
Memory Clock
2000 MHz 8 Gbps effective
1404 MHz 5.6 Gbps effective
Memory
Memory Size
90 GB
3 GB
VRAM (MB)
92,160
3,072 -96.7%
Memory Type
HBM3e
GDDR5
Memory Bus
4096 bit
192 bit
Bandwidth
4.10 TB/s
134.8 GB/s
Cache
L1 Cache
256 KB (per SM)
16 KB (per SMX)
L2 Cache
50 MB
384 KB
Performance
Pixel Rate
47.16 GPixel/s
12.96 GPixel/s
Texture Rate
1,163.3 GTexel/s
51.84 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
1,244.2 GFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
51.84 GFLOPS (1:24)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
AI/RT
Tensor Cores
592
Power
TDP
1000 W
80 W
TDP (W)
1,000
80 -92.0%
Suggested PSU
1400 W
250 W
Power Connectors
1x 6-pin
Architecture
Architecture
Blackwell
Kepler
GPU Name
GB100
GK106
Generation
Server Blackwell (Bxx)
Quadro Kepler (Kx000)
Process Size
5 nm
28 nm
Transistors
104,000 million
2,540 million
Die Size
221 mm²
Foundry
TSMC
TSMC
Density
11.5M / mm²
API Support
DirectX
12 (11_0)
OpenGL
4.6
Vulkan
1.2.175
OpenCL
3.0
3.0
CUDA
10.0
3.0
Shader Model
6.5 (5.1)
Physical
Slot Width
SXM Module
Single-slot
Length
241 mm 9.5 inches
Height
111 mm 4.4 inches
Outputs
No outputs
1x DVI2x DisplayPort 1.2
Bus Interface
PCIe 5.0 x16
PCIe 2.0 x16
Other
Launch Price
1,269 USD
Production
Active
End-of-life
Predecessor
Server Hopper
Quadro Fermi
Successor
Server Rubin
Quadro Maxwell
View B200 Details View Quadro K4000 Details