GPU Comparison

NVIDIA

GEFORCE

NVIDIA GeForce RTX 4090 Mobile

CORE STATE AD103

VRAM 16 GB

CLOCK SPEED 1695 MHz

TDP 120 W

BUS WIDTH 256 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2023

VS

NVIDIA

GEFORCE

H200 NVL

CORE STATE GH100

VRAM 141 GB

CLOCK SPEED 1785 MHz

TDP 600 W

BUS WIDTH 6144 bit

ARCHITECTURE Hopper

nm

PROCESS 5 nm

LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

geekbench_opencl

180,831

305,608

geekbench_vulkan

170,774

N/A

passmark_directx_10

173

N/A

passmark_directx_11

262

N/A

passmark_directx_12

107

N/A

passmark_directx_9

310

N/A

passmark_g2d

984

N/A

passmark_g3d

27,212

N/A

passmark_gpu_compute

12,347

N/A

DETAILED SPECIFICATIONS

SPECIFICATION

RTX 4090 Mobile

H200 NVL

Core Specs

Shading Units

9,728

16,896 +73.7%

Shaders

9,728

16,896 +73.7%

TMUs

304

528 +73.7%

ROPs

112

24 -78.6%

SM Count

76

132 +73.7%

Clocks

Base Clock

1335 MHz

1365 MHz

Boost Clock

1695 MHz

1785 MHz

Memory Clock

2250 MHz 18 Gbps effective

1593 MHz 6.4 Gbps effective

Memory

Memory Size

16 GB

141 GB

VRAM (MB)

16,384

144,384 +781.3%

Memory Type

GDDR6

HBM3e

Memory Bus

256 bit

6144 bit

Bandwidth

576.0 GB/s

4.89 TB/s

Cache

L1 Cache

128 KB (per SM)

256 KB (per SM)

L2 Cache

64 MB

50 MB

Performance

Pixel Rate

189.8 GPixel/s

42.84 GPixel/s

Texture Rate

515.3 GTexel/s

942.5 GTexel/s

FP32 (TFLOPS)

32.98 TFLOPS

60.32 TFLOPS

FP64 (TFLOPS)

515.3 GFLOPS (1:64)

30.16 TFLOPS (1:2)

FP16 (TFLOPS)

32.98 TFLOPS (1:1)

241.3 TFLOPS (4:1)

AI/RT

RT Cores

76

—

Tensor Cores

304

528 +73.7%

Power

TDP

120 W

600 W

TDP (W)

120

600 +400.0%

Suggested PSU

—

1000 W

Power Connectors

None

8-pin EPS

Architecture

Architecture

Ada Lovelace

Hopper

GPU Name

AD103

GH100

Generation

GeForce 40 Mobile

Server Hopper (Hxx)

Process Size

5 nm

5 nm

Transistors

45,900 million

80,000 million

Die Size

379 mm²

814 mm²

Foundry

TSMC

TSMC

Density

121.1M / mm²

98.3M / mm²

API Support

DirectX

12 Ultimate (12_2)

—

OpenGL

4.6

—

Vulkan

1.4

—

OpenCL

3.0

3.0

CUDA

8.9

9.0

Shader Model

6.8

—

Physical

Slot Width

IGP

Dual-slot

Length

—

267 mm 10.5 inches

Height

—

111 mm 4.4 inches

Outputs

Portable Device Dependent

No outputs

Bus Interface

PCIe 4.0 x16

PCIe 5.0 x16

Other

Production

Active

Active

Predecessor

GeForce 30 Mobile

Server Ada

Successor

GeForce 50 Mobile

Server Blackwell

View GeForce RTX 4090 Mobile Details View H200 NVL Details