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
Tesla M4
CORE STATE
GM206
VRAM
4 GB
CLOCK SPEED
1072 MHz
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
B200
Tesla M4
Core Specs
Shading Units
18,944
1,024
-94.6%
Shaders
18,944
1,024
-94.6%
TMUs
592
64
-89.2%
ROPs
24
32
+33.3%
SM Count
148
—
Clocks
Base Clock
700 MHz
872 MHz
Boost Clock
1965 MHz
1072 MHz
Memory Clock
2000 MHz
8 Gbps effective
1375 MHz
5.5 Gbps effective
Memory
Memory Size
90 GB
4 GB
VRAM (MB)
92,160
4,096
-95.6%
Memory Type
HBM3e
GDDR5
Memory Bus
4096 bit
128 bit
Bandwidth
4.10 TB/s
88.00 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SMM)
L2 Cache
50 MB
1024 KB
Performance
Pixel Rate
47.16 GPixel/s
34.30 GPixel/s
Texture Rate
1,163.3 GTexel/s
68.61 GTexel/s
FP32 (TFLOPS)
74.45 TFLOPS
2.195 TFLOPS
FP64 (TFLOPS)
37.22 TFLOPS (1:2)
68.61 GFLOPS (1:32)
FP16 (TFLOPS)
1,191.2 TFLOPS (16:1)
—
AI/RT
Tensor Cores
592
—
Power
TDP
1000 W
50 W
TDP (W)
1,000
50
-95.0%
Suggested PSU
1400 W
250 W
Architecture
Architecture
Blackwell
Maxwell 2.0
GPU Name
GB100
GM206
Generation
Server Blackwell
(Bxx)
Tesla Maxwell
(Mxx)
Process Size
5 nm
28 nm
Transistors
104,000 million
2,940 million
Die Size
—
228 mm²
Foundry
TSMC
TSMC
Density
—
12.9M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.0
5.2
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Single-slot
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
Active
End-of-life
Predecessor
Server Hopper
Tesla Kepler
Successor
Server Rubin
Tesla Pascal