GPU Comparison

NVIDIA

GEFORCE

NVIDIA 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

VS

NVIDIA

GEFORCE

Quadro RTX 4000

CORE STATE TU104

VRAM 8 GB

CLOCK SPEED 1545 MHz

TDP 160 W

BUS WIDTH 256 bit

ARCHITECTURE Turing

nm

PROCESS 12 nm

LAUNCH DATE 2018

PERFORMANCE BENCHMARKS

geekbench_opencl

305,608

85,166

3dmark_3dmark_steel_nomad_dx12

N/A

1,873

geekbench_vulkan

N/A

78,844

passmark_directx_10

N/A

108

passmark_directx_11

N/A

128

passmark_directx_12

N/A

52

passmark_directx_9

N/A

205

passmark_g2d

N/A

846

passmark_g3d

N/A

15,117

passmark_gpu_compute

N/A

6,176

DETAILED SPECIFICATIONS

SPECIFICATION

H200 NVL

Quadro RTX 4000

Core Specs

Shading Units

16,896

2,304 -86.4%

Shaders

16,896

2,304 -86.4%

TMUs

528

144 -72.7%

ROPs

24

64 +166.7%

SM Count

132

36 -72.7%

Clocks

Base Clock

1365 MHz

1005 MHz

Boost Clock

1785 MHz

1545 MHz

Memory Clock

1593 MHz 6.4 Gbps effective

1625 MHz 13 Gbps effective

Memory

Memory Size

141 GB

8 GB

VRAM (MB)

144,384

8,192 -94.3%

Memory Type

HBM3e

GDDR6

Memory Bus

6144 bit

256 bit

Bandwidth

4.89 TB/s

416.0 GB/s

Cache

L1 Cache

256 KB (per SM)

64 KB (per SM)

L2 Cache

50 MB

4 MB

Performance

Pixel Rate

42.84 GPixel/s

98.88 GPixel/s

Texture Rate

942.5 GTexel/s

222.5 GTexel/s

FP32 (TFLOPS)

60.32 TFLOPS

7.119 TFLOPS

FP64 (TFLOPS)

30.16 TFLOPS (1:2)

222.5 GFLOPS (1:32)

FP16 (TFLOPS)

241.3 TFLOPS (4:1)

14.24 TFLOPS (2:1)

AI/RT

RT Cores

—

36

Tensor Cores

528

288 -45.5%

Power

TDP

600 W

160 W

TDP (W)

600

160 -73.3%

Suggested PSU

1000 W

450 W

Power Connectors

8-pin EPS

1x 8-pin

Architecture

Architecture

Hopper

Turing

GPU Name

GH100

TU104

Generation

Server Hopper (Hxx)

Quadro Turing (Tx000)

Process Size

5 nm

12 nm

Transistors

80,000 million

13,600 million

Die Size

814 mm²

545 mm²

Foundry

TSMC

TSMC

Density

98.3M / mm²

25.0M / mm²

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

3.0

CUDA

9.0

7.5

Shader Model

—

6.8

Physical

Slot Width

Dual-slot

Single-slot

Length

267 mm 10.5 inches

241 mm 9.5 inches

Height

111 mm 4.4 inches

111 mm 4.4 inches

Outputs

No outputs

3x DisplayPort 1.4a1x USB Type-C

Bus Interface

PCIe 5.0 x16

PCIe 3.0 x16

Other

Launch Price

—

899 USD

Production

Active

End-of-life

Predecessor

Server Ada

Quadro Volta

Successor

Server Blackwell

Workstation Ampere

View H200 NVL Details View Quadro RTX 4000 Details