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
RTX 2000 Ada Generation
CORE STATE
AD107
VRAM
16 GB
CLOCK SPEED
2130 MHz
TDP
70 W
BUS WIDTH
128 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2024
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
B200
RTX 2000 Ada Generation
Core Specs
Shading Units
18,944
2,816
-85.1%
Shaders
18,944
2,816
-85.1%
TMUs
592
88
-85.1%
ROPs
24
48
+100.0%
SM Count
148
22
-85.1%
Clocks
Base Clock
700 MHz
1620 MHz
Boost Clock
1965 MHz
2130 MHz
Memory Clock
2000 MHz
8 Gbps effective
2000 MHz
16 Gbps effective
Memory
Memory Size
90 GB
16 GB
VRAM (MB)
92,160
16,384
-82.2%
Memory Type
HBM3e
GDDR6
Memory Bus
4096 bit
128 bit
Bandwidth
4.10 TB/s
256.0 GB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
12 MB
Performance
Pixel Rate
47.16 GPixel/s
102.2 GPixel/s
Texture Rate
1,163.3 GTexel/s
187.4 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
12.00 TFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
187.4 GFLOPS (1:64)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
12.00 TFLOPS (1:1)
AI/RT
RT Cores
—
22
Tensor Cores
592
88
-85.1%
Power
TDP
1000 W
70 W
TDP (W)
1,000
70
-93.0%
Suggested PSU
1400 W
250 W
Power Connectors
—
None
Architecture
Architecture
Blackwell
Ada Lovelace
GPU Name
GB100
AD107
Generation
Server Blackwell
(Bxx)
Workstation Ada
(x000A)
Process Size
5 nm
5 nm
Transistors
104,000 million
18,900 million
Die Size
—
159 mm²
Foundry
TSMC
TSMC
Density
—
118.9M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.0
8.9
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Dual-slot
Length
—
168 mm
6.6 inches
Height
—
69 mm
2.7 inches
Outputs
No outputs
4x mini-DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Other
Launch Price
—
649 USD
Production
Active
Active
Predecessor
Server Hopper
Workstation Ampere
Successor
Server Rubin
Blackwell PRO W