EVGA RTX 4090 FTW3 Prototype vs NVIDIA GeForce RTX 5090 Mobile

Comparison of EVGA RTX 4090 FTW3 Prototype with 24 GB GDDR6X and 16,384 cores vs NVIDIA GeForce RTX 5090 Mobile with 24 GB GDDR7 and 10,496 cores.

Loading...

Performance Rating

EVGA RTX 4090 FTW3 Prototype outperforms NVIDIA GeForce RTX 5090 Mobile by 75.1% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

EVGA RTX 4090 FTW3 Prototype

32.1

EVGA RTX 4090 FTW3 Prototype

32.1
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA GeForce RTX 5090 Mobile

18.3

NVIDIA GeForce RTX 5090 Mobile

18.3

Contents:

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

Memory

Memory Size

24 GB
🔥 24 ГБ

Memory Type

GDDR6X GDDR7

Memory Bandwidth

🔥 1.01 TB/s
896.0 GB/s

Memory Bus Width

384 бит 256 бит

ML Performance

FP16 (Half Precision)

82.58 TFLOPS
🔥 33.52 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

82.58 TFLOPS
🔥 33.52 TFLOPS

FP64 (Double Precision)

1.2902 TFLOPS
🔥 0.5238 TFLOPS

CUDA Cores

16,384
🔥 10,496

RT Cores

128
🔥 82

Architecture & Compatibility

GPU Architecture

Ada Lovelace Blackwell 2.0

SM (Streaming Multiprocessor)

128
🔥 82

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

8.9
🔥 12.0

Clocks & Performance

Base Clock

2,235
🔥 1,095

Boost Clock

2,520
🔥 1,597

Memory Clock

1,313
🔥 +33% 1,750

Power Consumption

Recommended PSU

850 W No

Power Connector

1x 16-pin None

TDP/TGP

450 W
🔥 -79% 95 W

Rendering

Texture Units (TMU)

512
🔥 328

ROP

128
🔥 82

L2 Cache

72 MB
🔥 64 MB

Additional

Slots

Quad-slot IGP

Release Date

No March 27, 2025

Display Outputs

1x HDMI 2.1
3x DisplayPort 1.4a
Portable Device Dependent

Renting is cheaper than buying