GPU Comparison

NVIDIA

GEFORCE

NVIDIA GeForce RTX 3050 OEM

CORE STATE GA106

VRAM 8 GB

CLOCK SPEED 1755 MHz

TDP 130 W

BUS WIDTH 128 bit

ARCHITECTURE Ampere

nm

PROCESS 8 nm

LAUNCH DATE 2022

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

60,740

305,608

geekbench_vulkan

57,103

N/A

passmark_directx_10

61

N/A

passmark_directx_11

86

N/A

passmark_directx_12

58

N/A

passmark_directx_9

137

N/A

passmark_g2d

973

N/A

passmark_g3d

11,857

N/A

passmark_gpu_compute

5,779

N/A

DETAILED SPECIFICATIONS

SPECIFICATION

RTX 3050 OEM

H200 NVL

Core Specs

Shading Units

2,304

16,896 +633.3%

Shaders

2,304

16,896 +633.3%

TMUs

72

528 +633.3%

ROPs

32

24 -25.0%

SM Count

18

132 +633.3%

Clocks

Base Clock

1515 MHz

1365 MHz

Boost Clock

1755 MHz

1785 MHz

Memory Clock

1750 MHz 14 Gbps effective

1593 MHz 6.4 Gbps effective

Memory

Memory Size

8 GB

141 GB

VRAM (MB)

8,192

144,384 +1662.5%

Memory Type

GDDR6

HBM3e

Memory Bus

128 bit

6144 bit

Bandwidth

224.0 GB/s

4.89 TB/s

Cache

L1 Cache

128 KB (per SM)

256 KB (per SM)

L2 Cache

2 MB

50 MB

Performance

Pixel Rate

56.16 GPixel/s

42.84 GPixel/s

Texture Rate

126.4 GTexel/s

942.5 GTexel/s

FP32 (TFLOPS)

8.087 TFLOPS

60.32 TFLOPS

FP64 (TFLOPS)

126.4 GFLOPS (1:64)

30.16 TFLOPS (1:2)

FP16 (TFLOPS)

8.087 TFLOPS (1:1)

241.3 TFLOPS (4:1)

AI/RT

RT Cores

18

—

Tensor Cores

72

528 +633.3%

Power

TDP

130 W

600 W

TDP (W)

130

600 +361.5%

Suggested PSU

300 W

1000 W

Power Connectors

1x 8-pin

8-pin EPS

Architecture

Architecture

Ampere

Hopper

GPU Name

GA106

GH100

Generation

GeForce 30

Server Hopper (Hxx)

Process Size

8 nm

5 nm

Transistors

12,000 million

80,000 million

Die Size

276 mm²

814 mm²

Foundry

Samsung

TSMC

Density

43.5M / mm²

98.3M / mm²

API Support

DirectX

12 Ultimate (12_2)

—

OpenGL

4.6

—

Vulkan

1.4

—

OpenCL

3.0

3.0

CUDA

8.6

9.0

Shader Model

6.8

—

Physical

Slot Width

Dual-slot

Dual-slot

Length

242 mm 9.5 inches

267 mm 10.5 inches

Height

112 mm 4.4 inches

111 mm 4.4 inches

Outputs

1x HDMI 2.13x DisplayPort 1.4a

No outputs

Bus Interface

PCIe 4.0 x8

PCIe 5.0 x16

Other

Production

End-of-life

Active

Predecessor

GeForce 20

Server Ada

Successor

GeForce 40

Server Blackwell

View GeForce RTX 3050 OEM Details View H200 NVL Details