NVIDIA CMP 90HX vs NVIDIA B100
We compared two Desktop platform GPUs: 10GB VRAM CMP 90HX and 96GB VRAM B100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 90HX 's Advantages
Lower TDP (320W vs 1000W)
NVIDIA B100 's Advantages
Released 3 years and 4 months late
Boost Clock has increased by 7% (1837MHz vs 1710MHz)
More VRAM (96GB vs 10GB)
Larger VRAM bandwidth (4.10TB/s vs 760.3GB/s)
10496 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 90HX
21.89 TFLOPS
B100
+183%
62.08 TFLOPS
Graphics Card
Jul 2021
Release Date
Nov 2024
Mining GPUs
Generation
Server Blackwell
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1665 MHz
1710 MHz
Boost Clock
1837 MHz
1188 MHz
Memory Clock
2000 MHz
Memory
10GB
Memory Size
96GB
GDDR6X
Memory Type
HBM3e
320bit
Memory Bus
4096bit
760.3GB/s
Bandwidth
4.10TB/s
Render Config
-
-
-
50
SM Count
132
6400
Shading Units
16896
200
TMUs
528
80
ROPs
24
200
Tensor Cores
528
50
RT Cores
-
128 KB (per SM)
L1 Cache
256 KB (per SM)
5 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
136.8 GPixel/s
Pixel Rate
44.09 GPixel/s
342.0 GTexel/s
Texture Rate
969.9 GTexel/s
21.89 TFLOPS
FP16 (half)
248.3 TFLOPS
21.89 TFLOPS
FP32 (float)
62.08 TFLOPS
342.0 GFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
320W
TDP
1000W
700 W
Suggested PSU
1400 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
-
Graphics Processor
GA102
GPU Name
GB102
GA102-100-A1
GPU Variant
-
Ampere
Architecture
Blackwell
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
28.3 billion
Transistors
104 billion
628 mm²
Die Size
Unknown
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
10.1
6.8
Shader Model
N/A
