NVIDIA GeForce RTX 5070 Ti SUPER vs NVIDIA P106-090

Comparison of NVIDIA GeForce RTX 5070 Ti SUPER with 16 GB GDDR7 and 8,960 cores vs NVIDIA P106-090 with 3 GB GDDR5 and 768 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA GeForce RTX 5070 Ti SUPER

NVIDIA GeForce RTX 5070 Ti SUPER

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

NVIDIA P106-090

2.2

NVIDIA P106-090

2.2

Contents:

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

Memory

Memory Size

16 GB 3 ГБ

Memory Type

GDDR7 GDDR5

Memory Bandwidth

896.0 GB/s 192.2 GB/s

Memory Bus Width

256 бит 192 бит

ML Performance

FP16 (Half Precision)

43.94 TFLOPS 36.74 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

43.94 TFLOPS 2.352 TFLOPS

FP64 (Double Precision)

0.6866 TFLOPS 0.07349 TFLOPS

CUDA Cores

8,960 768

RT Cores

70 No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Pascal

SM (Streaming Multiprocessor)

70 6

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 12.0
6.1

Clocks & Performance

Base Clock

2,295 1,354

Boost Clock

2,452 1,531

Memory Clock

1,750 2,002

Power Consumption

TDP/TGP

350 W
🔥 -79% 75 W

Recommended PSU

750 W
🔥 -67% 250 W

Power Connector

1x 16-pin 1x 6-pin

Rendering

Texture Units (TMU)

280 48

ROP

70 No

L2 Cache

48 MB 1536 KB

Additional

Slots

Dual-slot Dual-slot

Release Date

March 11, 2026 July 31, 2017

Display Outputs

1x HDMI 2.1b
3x DisplayPort 2.1b
No outputs

Renting is cheaper than buying