NVIDIA GeForce RTX 5070 Ti SUPER vs NVIDIA Tesla X2070

Comparison of NVIDIA GeForce RTX 5070 Ti SUPER with 16 GB GDDR7 and 8,960 cores vs NVIDIA Tesla X2070 with 6 GB GDDR5 and 448 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA GeForce RTX 5070 Ti SUPER

NVIDIA GeForce RTX 5070 Ti SUPER

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

NVIDIA Tesla X2070

NVIDIA Tesla X2070

Contents:

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

Memory

Memory Size

16 GB 6 GB

Memory Type

GDDR7 GDDR5

Memory Bandwidth

896.0 GB/s 177.4 GB/s

Memory Bus Width

256 бит 384 бит

ML Performance

FP16 (Half Precision)

43.94 TFLOPS No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

43.94 TFLOPS 1.1657 TFLOPS

FP64 (Double Precision)

0.6866 TFLOPS 0.5828 TFLOPS

CUDA Cores

8,960 448

RT Cores

70 No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Fermi

SM (Streaming Multiprocessor)

70 14

PCIe Version

PCIe 5.0 x16 MXM-B (3.0)

ML Software Support

CUDA Version

🔥 12.0
2.0

Clocks & Performance

Base Clock

2,295 No

Boost Clock

2,452 No

Memory Clock

1,750 924

Power Consumption

TDP/TGP

350 W
🔥 -36% 225 W

Recommended PSU

750 W
🔥 -27% 550 W

Power Connector

1x 16-pin None

Rendering

Texture Units (TMU)

280 56

ROP

70 No

L2 Cache

48 MB 768 KB

Benchmarks

llama.cpp, llama 7B Q4_0

14.3 tokens/s

llama.cpp, llama-2-7b-Q4_0

14.3 tokens/s

Additional

Slots

Dual-slot MXM Module

Release Date

March 11, 2026 July 25, 2011

Display Outputs

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

Renting is cheaper than buying