GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA GeForce RTX 3070 Founders Edition

Graphics processor

Video memory: 8 GB^*
Memory bus: 256 bit^*
Rated memory bandwidth: 448 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU cores: 5,888^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 392 mm²^*
Transistors: 17,400 million^*
GPU L2 cache: 4 MB^*
Graphics processor: GA104^*
Texture mapping units: 184^*
Raster output units: 96^*
Streaming multiprocessors: 46^*
Tensor cores: 184^*
Ray tracing cores: 46^*
Chip foundry: Samsung^*
Card or module format: Dual-slot^*
Declared GPU TDP: 220 W^*
Suggested system PSU: 550 W^*
External power connectors: 1x 12-pin^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 8.6^*
Shader model: 6.9^*

Memory & storage

Memory options: 8^*
Video memory: 8 GB^*
Video memory type: GDDR6^*
Memory bus: 256 bit^*
Rated memory bandwidth: 448 GB/s^*

Power specifications

Thermal design power: 220 W^*

System configuration

Detailed specifications

Specifications 1 · 31 fields

proc transistors: 17,400 million^*
proc die size: 392^* mm²
cores: 5,888^*
tensor cores: 184^*
rt cores: 46^*
sm count: 46^*
base clock: 1,500^*
boost clock: 1,725^*
memory clock: 1,750^*
ram: 8^*
name: NVIDIA GeForce RTX 3070 Founders Edition^*
ram type: GDDR6^*
bus width: 256^*
bus interface: PCIe 4.0 x16^*
ram bandwidth: 448^* GB/s
fp16 performance: 20.31^*
fp32 performance: 20.31^*
fp64 performance: 0.3174^*
tdp: 220^* W
suggested psu: 550^* W
slot width: Dual-slot^*
power connectors: 1x 12-pin^*
api cuda: 8.6^*
is retail board: Yes^*
gpi value: 10.26^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ampere^*
card release date: 2020-09-01^*
proc foundry: Samsung^*
proc process size: 8^* nm

Specifications 2 · 40 fields

CUDA compute capability

8.6^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Ampere^*

Graphics interface

PCIe 4.0 x16^*

Memory bus

256^* bit

Reported shader processors

5,888^*

Reported theoretical FP16 peak

20.31^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

20.31^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.3174^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

4 MB^*

Reported display outputs

1x HDMI 2.1, 3x DisplayPort 1.4a^*

Theoretical pixel fill rate

165.6 GPixel/s^*

External power connectors

1x 12-pin^*

Reported chip die area

392 mm²^*

Chip foundry

Samsung^*

Process node declaration

8 nm^*

Transistors

17,400 million^*

Graphics processor

GA104^*

Reported video memory

8^* GB

Rated memory bandwidth

448.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

96^*

Ray tracing cores

46^*

Reported shading units

5,888^*

Card or module format

Dual-slot^*

Streaming multiprocessors

46^*

Suggested system PSU

550 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

220 W^*

Tensor cores

184^*

Theoretical texture fill rate

317.4 GTexel/s^*

Texture mapping units

184^*

GPU cores

5,888^*

Video memory

8^* GB

Video memory type

GDDR6^*

* Provisional data