EVGA 9800 GTX+ Superclocked vs NVIDIA CMP 70HX

Comparison of EVGA 9800 GTX+ Superclocked with 512 GB GDDR3 and 128 cores vs NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

EVGA 9800 GTX+ Superclocked

EVGA 9800 GTX+ Superclocked

RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA CMP 70HX

NVIDIA CMP 70HX

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

512 MB 8 GB

Memory Type

GDDR3 GDDR6X

Memory Bandwidth

72.19 GB/s 608.3 GB/s

Memory Bus Width

256 бит 256 бит

ML Performance

FP16 (Half Precision)

No 10.71 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

0.4838 TFLOPS 10.71 TFLOPS

FP64 (Double Precision)

No 0.1674 TFLOPS

CUDA Cores

128 3,840

RT Cores

No 30

Architecture & Compatibility

GPU Architecture

Tesla Ampere

SM (Streaming Multiprocessor)

16 30

PCIe Version

PCIe 2.0 x16 PCIe 1.0 x4

ML Software Support

CUDA Version

1.1
🔥 8.6

Clocks & Performance

Base Clock

No 1,365

Boost Clock

No 1,395

Memory Clock

1,128 1,188

Power Consumption

TDP/TGP

141 W unknown

Recommended PSU

300 W
🔥 -33% 200 W

Power Connector

2x 6-pin 1x 12-pin

Rendering

Texture Units (TMU)

64 120

ROP

No 30

L2 Cache

64 KB 4 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

Jan. 16, 2009 March 11, 2021

Display Outputs

2x DVI
1x S-Video

2x DVI
1x HDMI
No outputs

Renting is cheaper than buying