NVIDIA GeForce RTX 5090 Mobile vs SPARKLE Calibre GTX 680 Captain

Comparison of NVIDIA GeForce RTX 5090 Mobile with 24 GB GDDR7 and 10,496 cores vs SPARKLE Calibre GTX 680 Captain with 2 GB GDDR5 and 1,536 cores.

Loading...

Performance Rating

NVIDIA GeForce RTX 5090 Mobile outperforms SPARKLE Calibre GTX 680 Captain by 563.41% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA GeForce RTX 5090 Mobile

18.3

NVIDIA GeForce RTX 5090 Mobile

18.3
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

SPARKLE Calibre GTX 680 Captain

2.8

SPARKLE Calibre GTX 680 Captain

2.8

Contents:

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

Memory

Memory Size

🔥 +1,100% 24 ГБ
2 GB

Memory Type

GDDR7 GDDR5

Memory Bandwidth

896.0 GB/s 198.4 GB/s

Memory Bus Width

256 бит 256 бит

ML Performance

FP16 (Half Precision)

🔥 33.52 TFLOPS
No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +818% 33.52 TFLOPS
3.653 TFLOPS

FP64 (Double Precision)

🔥 +244% 0.5238 TFLOPS
0.1522 TFLOPS

CUDA Cores

🔥 +583% 10,496
1,536

RT Cores

🔥 82
No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Kepler

SM (Streaming Multiprocessor)

🔥 82
No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 12.0
3.0

Clocks & Performance

Base Clock

🔥 1,095
1,124

Boost Clock

🔥 +34% 1,597
1,189

Memory Clock

🔥 +13% 1,750
1,550

Power Consumption

Recommended PSU

No 450 W

Power Connector

None 2x 6-pin

TDP/TGP

🔥 -51% 95 W
195 W

Rendering

Texture Units (TMU)

🔥 +156% 328
128

ROP

🔥 82
No

L2 Cache

🔥 64 MB
512 KB

Additional

Slots

IGP Dual-slot

Release Date

March 27, 2025 Sept. 3, 2012

Display Outputs

Portable Device Dependent
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2

Renting is cheaper than buying