Gainward RTX 4090 D Glare vs NVIDIA B300

Comparison of Gainward RTX 4090 D Glare with 24 GB GDDR6X and 14,592 cores vs NVIDIA B300 with 144 GB HBM3e and 18,944 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms Gainward RTX 4090 D Glare by 139.13% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Gainward RTX 4090 D Glare

30.1

Gainward RTX 4090 D Glare

30.1
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA B300

71.9

NVIDIA B300

71.9

Contents:

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

Memory

Memory Size

24 GB
🔥 +500% 144 ГБ ×2 (288 ГБ)

Memory Type

GDDR6X HBM3e

Memory Bandwidth

1.01 TB/s
🔥 +306% 4.10 TB/s ×2 (8.2 TB/s)

Memory Bus Width

384 бит 4,096 бит ×2 (8192 бит)

ML Performance

FP16 (Half Precision)

🔥 +5,870% 73.54 TFLOPS
1.2318 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

73.54 TFLOPS
🔥 +5% 76.99 TFLOPS

FP64 (Double Precision)

1.1491 TFLOPS
🔥 +5% 1.2029 TFLOPS

CUDA Cores

14,592
🔥 +30% 18,944 ×2 (37888)

RT Cores

🔥 114
No

Architecture & Compatibility

GPU Architecture

Ada Lovelace Blackwell Ultra

SM (Streaming Multiprocessor)

114
🔥 +30% 148

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

8.9
🔥 10.3

Clocks & Performance

Base Clock

🔥 +37% 2,280
1,665

Boost Clock

🔥 +24% 2,520
2,032

Memory Clock

1,313
🔥 +52% 2,000

Power Consumption

Recommended PSU

🔥 -56% 800 W
1800 W

Power Connector

1x 16-pin No

TDP/TGP

🔥 -70% 425 W
1400 W

Rendering

Texture Units (TMU)

456
🔥 +30% 592 ×2 (1184)

ROP

🔥 114
No

L2 Cache

🔥 +44% 72 MB
50 MB

Additional

Slots

Quad-slot
🔥 SXM Module

Release Date

Dec. 28, 2023 Sept. 11, 2025

Display Outputs

1x HDMI 2.1
3x DisplayPort 1.4a
No outputs

Renting is cheaper than buying