GPU Comparison

NVIDIA
GEFORCE

NVIDIA CMP 90HX

CORE STATE GA102
VRAM 10 GB
CLOCK SPEED 1710 MHz
TDP 320 W
BUS WIDTH 320 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2021
VS
NVIDIA
GEFORCE

RTX PRO 6000 Blackwell Server

CORE STATE GB202
VRAM 96 GB
CLOCK SPEED 2617 MHz
TDP 600 W
BUS WIDTH 512 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

geekbench_opencl
69,000
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
5,996

Analysis: NVIDIA CMP 90HX vs NVIDIA RTX PRO 6000 Blackwell Server

Examining the test results for the NVIDIA RTX PRO 6000 Blackwell Server card from NVIDIA and NVIDIA's NVIDIA CMP 90HX graphics, a picture of similar throughput emerges. Neither GPU excels reliably throughout the titles. The back-and-forth of leads suggests core equality. Those confront a real decision between them. Both cards deliver competent gaming results.

As opposed to fixating on slight benchmark advantages, future consumers can examine additional considerations. thermal performance, noise levels, design, and service options usually are important greater than small FPS deltas. Such variables could tip the decision. Evaluate further than simply performance. The full value proposition matters.

In conclusion, the evaluation between the NVIDIA RTX PRO 6000 Blackwell Server card from NVIDIA and NVIDIA's NVIDIA CMP 90HX graphics finishes in a virtual deadlock. Frame rate variations are small and questionable to change actual sessions. Concentrate your decision on cost, ecosystem preferences, and specific extra needs. Each are strong picks. This parity is genuine.

DETAILED SPECIFICATIONS

SPECIFICATION
CMP 90HX
RTX PRO 6000 Blackwell Server
Core Specs
Shading Units
6,400
24,064 +276.0%
Shaders
6,400
24,064 +276.0%
TMUs
200
752 +276.0%
ROPs
80
192 +140.0%
SM Count
50
188 +276.0%
Clocks
Base Clock
1500 MHz
1590 MHz
Boost Clock
1710 MHz
2617 MHz
Memory Clock
1188 MHz 19 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
10 GB
96 GB
VRAM (MB)
10,240
98,304 +860.0%
Memory Type
GDDR6X
GDDR7
Memory Bus
320 bit
512 bit
Bandwidth
760.3 GB/s
1.79 TB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
5 MB
128 MB
Performance
Pixel Rate
136.8 GPixel/s
502.5 GPixel/s
Texture Rate
342.0 GTexel/s
1,968.0 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
126.0 TFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
1.968 TFLOPS (1:64)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
126.0 TFLOPS (1:1)
AI/RT
RT Cores
50
188 +276.0%
Tensor Cores
200
752 +276.0%
Power
TDP
320 W
600 W
TDP (W)
320
600 +87.5%
Suggested PSU
700 W
1000 W
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
Ampere
Blackwell 2.0
GPU Name
GA102
GB202
Generation
Mining GPUs
Server Blackwell (Bxx)
Process Size
8 nm
5 nm
Transistors
28,300 million
92,200 million
Die Size
628 mm²
750 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
122.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.6
12.0
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
285 mm 11.2 inches
267 mm 10.5 inches
Height
112 mm 4.4 inches
111 mm 4.4 inches
Outputs
No outputs
4x DisplayPort 2.1b
Bus Interface
PCIe 1.0 x4
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
Server Hopper
Successor
Server Rubin
View CMP 90HX Details View RTX PRO 6000 Blackwell Server Details