GPU Comparison

NVIDIA

GEFORCE

NVIDIA B200

CORE STATE GB100

VRAM 90 GB

CLOCK SPEED 1965 MHz

TDP 1000 W

BUS WIDTH 4096 bit

ARCHITECTURE Blackwell

nm

PROCESS 5 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

GeForce RTX 4090

CORE STATE AD102

VRAM 24 GB

CLOCK SPEED 2520 MHz

TDP 450 W

BUS WIDTH 384 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl

345,482

254,291

3dmark_3dmark_steel_nomad_dx12

N/A

9,223

geekbench_vulkan

N/A

259,107

passmark_directx_10

N/A

224

passmark_directx_11

N/A

326

passmark_directx_12

N/A

150

passmark_directx_9

N/A

397

passmark_g2d

N/A

1,299

passmark_g3d

N/A

38,194

passmark_gpu_compute

N/A

26,613

DETAILED SPECIFICATIONS

SPECIFICATION

B200

RTX 4090

Core Specs

Shading Units

18,944

16,384 -13.5%

Shaders

18,944

16,384 -13.5%

TMUs

592

512 -13.5%

ROPs

24

176 +633.3%

SM Count

148

128 -13.5%

Clocks

Base Clock

700 MHz

2235 MHz

Boost Clock

1965 MHz

2520 MHz

Memory Clock

2000 MHz 8 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

90 GB

24 GB

VRAM (MB)

92,160

24,576 -73.3%

Memory Type

HBM3e

GDDR6X

Memory Bus

4096 bit

384 bit

Bandwidth

4.10 TB/s

1.01 TB/s

Cache

L1 Cache

256 KB (per SM)

128 KB (per SM)

L2 Cache

50 MB

72 MB

Performance

Pixel Rate

47.16 GPixel/s

443.5 GPixel/s

Texture Rate

1,163.3 GTexel/s

1,290.2 GTexel/s

FP32 (TFLOPS)

74.45 TFLOPS

82.58 TFLOPS

FP64 (TFLOPS)

37.22 TFLOPS (1:2)

1,290.2 GFLOPS (1:64)

FP16 (TFLOPS)

1,191.2 TFLOPS (16:1)

82.58 TFLOPS (1:1)

AI/RT

RT Cores

—

128

Tensor Cores

592

512 -13.5%

Power

TDP

1000 W

450 W

TDP (W)

1,000

450 -55.0%

Suggested PSU

1400 W

850 W

Power Connectors

—

1x 16-pin

Architecture

Architecture

Blackwell

Ada Lovelace

GPU Name

GB100

AD102

Generation

Server Blackwell (Bxx)

GeForce 40

Process Size

5 nm

5 nm

Transistors

104,000 million

76,300 million

Die Size

—

609 mm²

Foundry

TSMC

TSMC

Density

—

125.3M / mm²

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

3.0

CUDA

10.0

8.9

Shader Model

—

6.8

Physical

Slot Width

SXM Module

Triple-slot

Length

—

304 mm 12 inches

Height

—

137 mm 5.4 inches

Outputs

No outputs

1x HDMI 2.13x DisplayPort 1.4a

Bus Interface

PCIe 5.0 x16

PCIe 4.0 x16

Other

Launch Price

—

1,599 USD

Production

Active

End-of-life

Predecessor

Server Hopper

GeForce 30

Successor

Server Rubin

GeForce 50

View B200 Details View GeForce RTX 4090 Details