GPU Comparison

NVIDIA

GEFORCE

NVIDIA GeForce RTX 2070

CORE STATE TU106

VRAM 8 GB

CLOCK SPEED 1620 MHz

TDP 175 W

BUS WIDTH 256 bit

ARCHITECTURE Turing

nm

PROCESS 12 nm

LAUNCH DATE 2018

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

3dmark_3dmark_steel_nomad_dx12

1,569

N/A

geekbench_opencl

88,108

305,608

geekbench_vulkan

83,291

N/A

passmark_directx_10

111

N/A

passmark_directx_11

129

N/A

passmark_directx_12

60

N/A

passmark_directx_9

211

N/A

passmark_g2d

819

N/A

passmark_g3d

16,094

N/A

passmark_gpu_compute

6,411

N/A

DETAILED SPECIFICATIONS

SPECIFICATION

RTX 2070

H200 NVL

Core Specs

Shading Units

2,304

16,896 +633.3%

Shaders

2,304

16,896 +633.3%

TMUs

144

528 +266.7%

ROPs

64

24 -62.5%

SM Count

36

132 +266.7%

Clocks

Base Clock

1410 MHz

1365 MHz

Boost Clock

1620 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

256 bit

6144 bit

Bandwidth

448.0 GB/s

4.89 TB/s

Cache

L1 Cache

64 KB (per SM)

256 KB (per SM)

L2 Cache

4 MB

50 MB

Performance

Pixel Rate

103.7 GPixel/s

42.84 GPixel/s

Texture Rate

233.3 GTexel/s

942.5 GTexel/s

FP32 (TFLOPS)

7.465 TFLOPS

60.32 TFLOPS

FP64 (TFLOPS)

233.3 GFLOPS (1:32)

30.16 TFLOPS (1:2)

FP16 (TFLOPS)

14.93 TFLOPS (2:1)

241.3 TFLOPS (4:1)

AI/RT

RT Cores

36

—

Tensor Cores

288

528 +83.3%

Power

TDP

175 W

600 W

TDP (W)

175

600 +242.9%

Suggested PSU

450 W

1000 W

Power Connectors

1x 8-pin

8-pin EPS

Architecture

Architecture

Turing

Hopper

GPU Name

TU106

GH100

Generation

GeForce 20

Server Hopper (Hxx)

Process Size

12 nm

5 nm

Transistors

10,800 million

80,000 million

Die Size

445 mm²

814 mm²

Foundry

TSMC

TSMC

Density

24.3M / mm²

98.3M / mm²

API Support

DirectX

12 Ultimate (12_2)

—

OpenGL

4.6

—

Vulkan

1.4

—

OpenCL

3.0

3.0

CUDA

7.5

9.0

Shader Model

6.8

—

Physical

Slot Width

Dual-slot

Dual-slot

Length

229 mm 9 inches

267 mm 10.5 inches

Height

113 mm 4.4 inches

111 mm 4.4 inches

Outputs

1x DVI1x HDMI 2.02x DisplayPort 1.4a1x USB Type-C

No outputs

Bus Interface

PCIe 3.0 x16

PCIe 5.0 x16

Other

Launch Price

499 USD

—

Production

End-of-life

Active

Predecessor

GeForce 10

Server Ada

Successor

GeForce 30

Server Blackwell

View GeForce RTX 2070 Details View H200 NVL Details