GPU Comparison

NVIDIA

GEFORCE

NVIDIA GeForce RTX 4070

CORE STATE AD104

VRAM 12 GB

CLOCK SPEED 2475 MHz

TDP 200 W

BUS WIDTH 192 bit

ARCHITECTURE Ada Lovelace

nm

PROCESS 5 nm

LAUNCH DATE 2023

VS

NVIDIA

GEFORCE

Tesla K20m

CORE STATE GK110

VRAM 5 GB

CLOCK SPEED —

TDP 225 W

BUS WIDTH 320 bit

ARCHITECTURE Kepler

nm

PROCESS 28 nm

LAUNCH DATE 2013

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12

3,854

N/A

geekbench_opencl

168,006

16,085

geekbench_vulkan

157,352

21,936

passmark_directx_10

139

N/A

passmark_directx_11

244

N/A

passmark_directx_12

103

N/A

passmark_directx_9

320

N/A

passmark_g2d

1,164

N/A

passmark_g3d

26,927

N/A

passmark_gpu_compute

14,720

N/A

DETAILED SPECIFICATIONS

SPECIFICATION

RTX 4070

Tesla K20m

Core Specs

Shading Units

5,888

2,496 -57.6%

Shaders

5,888

2,496 -57.6%

TMUs

184

208 +13.0%

ROPs

64

40 -37.5%

SM Count

46

—

Clocks

Base Clock

1920 MHz

—

Boost Clock

2475 MHz

—

GPU Clock

—

706 MHz

Memory Clock

1313 MHz 21 Gbps effective

1300 MHz 5.2 Gbps effective

Memory

Memory Size

12 GB

5 GB

VRAM (MB)

12,288

5,120 -58.3%

Memory Type

GDDR6X

GDDR5

Memory Bus

192 bit

320 bit

Bandwidth

504.2 GB/s

208.0 GB/s

Cache

L1 Cache

128 KB (per SM)

16 KB (per SMX)

L2 Cache

36 MB

1280 KB

Performance

Pixel Rate

158.4 GPixel/s

36.71 GPixel/s

Texture Rate

455.4 GTexel/s

146.8 GTexel/s

FP32 (TFLOPS)

29.15 TFLOPS

3.524 TFLOPS

FP64 (TFLOPS)

455.4 GFLOPS (1:64)

1,174.8 GFLOPS (1:3)

FP16 (TFLOPS)

29.15 TFLOPS (1:1)

—

AI/RT

RT Cores

46

—

Tensor Cores

184

—

Power

TDP

200 W

225 W

TDP (W)

200

225 +12.5%

Suggested PSU

550 W

550 W

Power Connectors

1x 16-pin

1x 6-pin + 1x 8-pin

Architecture

Architecture

Ada Lovelace

Kepler

GPU Name

AD104

GK110

Generation

GeForce 40

Tesla Kepler (Kxx)

Process Size

5 nm

28 nm

Transistors

35,800 million

7,080 million

Die Size

294 mm²

561 mm²

Foundry

TSMC

TSMC

Density

121.8M / mm²

12.6M / mm²

API Support

DirectX

12 Ultimate (12_2)

12 (11_0)

OpenGL

4.6

4.6

Vulkan

1.4

1.2.175

OpenCL

3.0

3.0

CUDA

8.9

3.5

Shader Model

6.8

6.5 (5.1)

Physical

Slot Width

Dual-slot

Dual-slot

Length

240 mm 9.4 inches

267 mm 10.5 inches

Height

110 mm 4.3 inches

—

Outputs

1x HDMI 2.13x DisplayPort 1.4a

No outputs

Bus Interface

PCIe 4.0 x16

PCIe 2.0 x16

Other

Launch Price

599 USD

3,199 USD

Production

End-of-life

End-of-life

Predecessor

GeForce 30

Tesla Fermi

Successor

GeForce 50

Tesla Maxwell

View GeForce RTX 4070 Details View Tesla K20m Details