GPU Comparison
GEFORCE
NVIDIA B200
CORE STATE
GB100
VRAM
90 GB
CLOCK SPEED
1965 MHz
TDP
1000 W
BUS WIDTH
4096 bit
ARCHITECTURE
Blackwell
PROCESS
5 nm
LAUNCH DATE
—
VS
GEFORCE
GeForce RTX 3090 Ti
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1860 MHz
TDP
450 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
B200
RTX 3090 Ti
Core Specs
Shading Units
18,944
10,752
-43.2%
Shaders
18,944
10,752
-43.2%
TMUs
592
336
-43.2%
ROPs
24
112
+366.7%
SM Count
148
84
-43.2%
Clocks
Base Clock
700 MHz
1560 MHz
Boost Clock
1965 MHz
1860 MHz
Memory Clock
2000 MHz
8 Gbps effective
1313 MHz
21 Gbps effective
Memory
Memory Size
90 GB
24 GB
VRAM (MB)
92,160
24,576
-73.3%
Memory Type
HBM3e
GDDR6X
Memory Bus
4096 bit
384 bit
Bandwidth
4.10 TB/s
1.01 TB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
6 MB
Performance
Pixel Rate
47.16 GPixel/s
208.3 GPixel/s
Texture Rate
1,163.3 GTexel/s
625.0 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
40.00 TFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
625.0 GFLOPS (1:64)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
40.00 TFLOPS (1:1)
AI/RT
RT Cores
—
84
Tensor Cores
592
336
-43.2%
Power
TDP
1000 W
450 W
TDP (W)
1,000
450
-55.0%
Suggested PSU
1400 W
850 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
Blackwell
Ampere
GPU Name
GB100
GA102
Generation
Server Blackwell
(Bxx)
GeForce 30
Process Size
5 nm
8 nm
Transistors
104,000 million
28,300 million
Die Size
—
628 mm²
Foundry
TSMC
Samsung
Density
—
45.1M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.0
8.6
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Triple-slot
Length
—
336 mm
13.2 inches
Height
—
140 mm
5.5 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Launch Price
—
1,999 USD
Production
Active
End-of-life
Predecessor
Server Hopper
GeForce 20
Successor
Server Rubin
GeForce 40