GPU Comparison

NVIDIA

GEFORCE

NVIDIA GB10

CORE STATE GB20B

VRAM 128 GB

CLOCK SPEED 2418 MHz

TDP 140 W

BUS WIDTH 256 bit

ARCHITECTURE Blackwell 2.0

PROCESS 5 nm

LAUNCH DATE 2025

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

PROCESS 5 nm

LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl

120,027

254,291

geekbench_vulkan

114,648

259,107

3dmark_3dmark_steel_nomad_dx12

N/A

9,223

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

Analysis: NVIDIA GB10 vs NVIDIA GeForce RTX 4090

Analyzing the test numbers for NVIDIA's RTX 4090 and the NVIDIA GB10 card from NVIDIA, the pattern of similar frame rates emerges. None of the graphics card dominates steadily across all titles. The back-and-forth of advantages implies fundamental balance. Consumers face a true dilemma in this matchup. Each GPUs offer solid visual throughput.

Game performance performance similarly reveal matched results between NVIDIA's RTX 4090 and the NVIDIA GB10 card from NVIDIA. Performance variations usually fall inside 5-10%. Such marginal gaps are rarely detectable during everyday play sessions. Either cards achieve smooth frame rates. Those who game could choose assuredly between these two.

When those torn between NVIDIA's RTX 4090 and the NVIDIA GB10 card from NVIDIA, rest assured that both selection offers similar graphics results. The benchmark numbers supports no obvious champion. Base your decision on alternative factors and appreciate solid visual performance regardless. Each are winners in their respective way. Choose confidently.

DETAILED SPECIFICATIONS

SPECIFICATION

GB10

RTX 4090

Core Specs

Shading Units

6,144

16,384 +166.7%

Shaders

6,144

16,384 +166.7%

TMUs

384

512 +33.3%

ROPs

176 +266.7%

SM Count

128 +166.7%

Clocks

Base Clock

1665 MHz

2235 MHz

Boost Clock

2418 MHz

2520 MHz

Memory Clock

1067 MHz 8.5 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

128 GB

24 GB

VRAM (MB)

131,072

24,576 -81.3%

Memory Type

LPDDR5X

GDDR6X

Memory Bus

256 bit

384 bit

Bandwidth

273.2 GB/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

116.1 GPixel/s

443.5 GPixel/s

Texture Rate

928.5 GTexel/s

1,290.2 GTexel/s

FP32 (TFLOPS)

29.71 TFLOPS

82.58 TFLOPS

FP64 (TFLOPS)

464.3 GFLOPS (1:64)

1,290.2 GFLOPS (1:64)

FP16 (TFLOPS)

29.71 TFLOPS (1:1)

82.58 TFLOPS (1:1)

AI/RT

RT Cores

128 +166.7%

Tensor Cores

384

512 +33.3%

Power

TDP

140 W

450 W

TDP (W)

140

450 +221.4%

Suggested PSU

300 W

850 W

Power Connectors

None

1x 16-pin

Architecture

Blackwell 2.0

Ada Lovelace

GPU Name

GB20B

AD102

Generation

Server Blackwell (Bxx)

GeForce 40

Process Size

5 nm

Transistors

—

76,300 million

Die Size

—

609 mm²

Foundry

TSMC

Density

—

125.3M / mm²

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

CUDA

12.1

8.9

Shader Model

—

6.8

Physical

Slot Width

IGP

Triple-slot

Length

150 mm 5.9 inches

304 mm 12 inches

Height

51 mm 2 inches

137 mm 5.4 inches

Outputs

1x HDMI

1x HDMI 2.13x DisplayPort 1.4a

Bus Interface

PCIe 5.0 x16

PCIe 4.0 x16

Other

Launch Price

3,999 USD

1,599 USD

Production

Active

End-of-life

Predecessor

Server Hopper

GeForce 30

Successor

Server Rubin

GeForce 50

View GB10 Details View GeForce RTX 4090 Details