NVIDIA GeForce RTX 3090 vs NVIDIA B200 SXM 192 GB

VS

NVIDIA GeForce RTX 3090 NVIDIA B200 SXM 192 GB

We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 3090 and 96GB VRAM B200 SXM 192 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 3090 's Advantages

Lower TDP (350W vs 1000W)

NVIDIA B200 SXM 192 GB 's Advantages

Released 3 years and 4 months late

Boost Clock has increased by 8% (1837MHz vs 1695MHz)

More VRAM (96GB vs 24GB)

Larger VRAM bandwidth (4100GB/s vs 936.2GB/s)

6400 additional rendering cores

Score

Benchmark

FP32 (float)

GeForce RTX 3090

35.58 TFLOPS

B200 SXM 192 GB +74%

62.08 TFLOPS

GeForce RTX 3090

VS

B200 SXM 192 GB

Graphics Card

Sep 2020

Release Date

Jan 2024

GeForce 30

Generation

Tesla Blackwell

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 5.0 x16

Clock Speeds

1395 MHz

Base Clock

1665 MHz

1695 MHz

Boost Clock

1837 MHz

1219 MHz

Memory Clock

2000 MHz

Memory

24GB

Memory Size

96GB

GDDR6X

Memory Type

HBM3e

384bit

Memory Bus

4096bit

936.2GB/s

Bandwidth

4100GB/s

Render Config

82

SM Count

132

-

Compute Units

-

10496

Shading Units

16896

328

TMUs

528

112

ROPs

24

328

Tensor Cores

528

82

RT Cores

-

128 KB (per SM)

L1 Cache

256 KB (per SM)

6 MB

L2 Cache

50 MB

Theoretical Performance

189.8 GPixel/s

Pixel Rate

44.09 GPixel/s

556.0 GTexel/s

Texture Rate

969.9 GTexel/s

35.58 TFLOPS

FP16 (half)

248.3 TFLOPS

35.58 TFLOPS

FP32 (float)

62.08 TFLOPS

556.0 GFLOPS

FP64 (double)

31.04 TFLOPS

Graphics Processor

GA102

GPU Name

GB100

GA102-300-A1

GPU Variant

-

Ampere

Architecture

Blackwell

Samsung

Foundry

TSMC

8 nm

Process Size

5 nm

28.3 billion

Transistors

208 billion

628 mm²

Die Size

Unknown

Board Design

350W

TDP

1000W

750 W

Suggested PSU

1400 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

No outputs

1x 12-pin

Power Connectors

-

Graphics Features

12 Ultimate (12_2)

DirectX

N/A

4.6

OpenGL

N/A

3.0

OpenCL

3.0

1.3

Vulkan

N/A

8.6

CUDA

9.0

6.6

Shader Model

N/A

Related GPU Comparisons

1

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4060

2

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4080

3

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4070

4

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4070 Ti

5

NVIDIA GeForce RTX 4060 Ti vs NVIDIA GeForce RTX 3090

6

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 3090

7

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 4080 SUPER

8

NVIDIA GeForce RTX 3090 vs NVIDIA RTX 4500 Ada Generation

9

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce GT 645 OEM

10

NVIDIA GeForce RTX 3090 vs AMD Radeon HD 6770 Green Edition

Related News

1

NVIDIA Informs Brands of Reduced Supply for RTX 40 Series GPUs

2

Only 3 Weeks Left! AMD Zen5 Launching Soon

3

Ilya Departs OpenAI to Launch New Company Aiming at Superintelligence!

4

Comprehensive Overview of AMD Ryzen 9000 Zen5 Desktop CPUs

5

Intel May Increase Base Frequencies for Arrow Lake-S / H / HX, High-End Chips to Reach 3GHz or Higher

6

It's 2024: This Company Released a Laptop Supporting DOS and Windows 95

7

AMD's Strix Halo Supports Up to 128GB Memory, Clearly Designed for AI Large Language Models

8

AMD to Launch Advanced Ryzen AI PRO Series Soon

9

Intel Delays Lunar Lake Shipment: Postponed from June to September

10

Initial Test Results of AMD Ryzen AI 9 365 Revealed: IPC Improvement Meets Expectations