GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

GeForce RTX 3060 3840SP

Graphics processor

Video memory: 6 GB^*
Memory bus: 192 bit^*
Rated memory bandwidth: 336 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU cores: 3,840^*
GPU base clock: 1,627 MHz^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 276 mm²^*
Transistors: 12,000 million^*
GPU boost clock: 1,852 MHz^*
GPU L2 cache: 3 MB^*
Graphics processor: GA106^*
Texture mapping units: 120^*
Raster output units: 48^*
Streaming multiprocessors: 30^*
Tensor cores: 120^*
Ray tracing cores: 30^*
Chip foundry: Samsung^*
Card or module format: Dual-slot^*
Declared GPU TDP: 185 W^*
Suggested system PSU: 450 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: 6^*
Video memory: 6 GB^*
Video memory type: GDDR6^*
Memory bus: 192 bit^*
Rated memory bandwidth: 336 GB/s^*

Power specifications

Thermal design power: 185 W^*

System configuration

Detailed specifications

Specifications 1 · 31 fields

proc transistors: 12,000 million^*
proc die size: 276^* mm²
cores: 3,840^*
tensor cores: 120^*
rt cores: 30^*
sm count: 30^*
base clock: 1,627^*
boost clock: 1,852^*
memory clock: 1,750^*
ram: 6^*
name: NVIDIA GeForce RTX 3060 3840SP^*
ram type: GDDR6^*
bus width: 192^*
bus interface: PCIe 4.0 x16^*
ram bandwidth: 336^* GB/s
fp16 performance: 14.22^*
fp32 performance: 14.22^*
fp64 performance: 0.2222^*
tdp: 185^* W
suggested psu: 450^* W
slot width: Dual-slot^*
power connectors: 1x 12-pin^*
api cuda: 8.6^*
is retail board: No^*
gpi value: 7.41^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ampere^*
card release date: 2021-03-11^*
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

192^* bit

Reported shader processors

3,840^*

Reported theoretical FP16 peak

14.22^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

14.22^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.2222^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

3 MB^*

Reported display outputs

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

Theoretical pixel fill rate

88.90 GPixel/s^*

External power connectors

1x 12-pin^*

Reported chip die area

276 mm²^*

Chip foundry

Samsung^*

Process node declaration

8 nm^*

Transistors

12,000 million^*

Graphics processor

GA106^*

Reported video memory

6^* GB

Rated memory bandwidth

336.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

48^*

Ray tracing cores

30^*

Reported shading units

3,840^*

Card or module format

Dual-slot^*

Streaming multiprocessors

30^*

Suggested system PSU

450 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

185 W^*

Tensor cores

120^*

Theoretical texture fill rate

222.2 GTexel/s^*

Texture mapping units

120^*

GPU cores

3,840^*

Video memory

6^* GB

Video memory type

GDDR6^*

Specifications 3 · 61 fields

Brand: NVIDIA^*
Top BUS WIDTH: 192^* bit
Graphics Processor GPU Name: GA106^*
Graphics Processor Architecture: Ampere^*
Render Config SM Count: 30^*
Graphics Features CUDA: 8.6^*
Render Config Tensor Cores: 120^*
Graphics Processor Process Size: 8^* nm
Graphics Processor Transistors: 12,000 million^*
Graphics Processor Die Size: 276^* mm²
Graphics Card Release Date: 2021^*
Graphics Card Generation: GeForce 30^*
Graphics Card Successor: GeForce 40^*
Graphics Card Production: Active^*
Name: GeForce RTX 3060 3840SP^*
Graphics Card Bus Interface: PCIe 4.0 x16^*
Clock Speeds Memory Clock: 1750 MHz 14 Gbps effective^*
Memory Memory Size: 6^* GB
Memory Memory Type: GDDR6^*
Memory Memory Bus: 192^* bit
Memory Bandwidth: 336^* GB/s
Render Config TMUs: 120^*
Top GRAPHICS PROCESSOR: GA106^*
Render Config ROPs: 48^*
Theoretical Performance Pixel Rate: 88.90 GPixel/s
Theoretical Performance Texture Rate: 222.2 GTexel/s
Board Design Slot Width: Dual-slot^*
Board Design TDP: 185^* W
Board Design Suggested PSU: 450^* W
Board Design Outputs: 1x HDMI 2.1 3x DisplayPort 1.4a^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2021.json^*
Graphics Processor Foundry: Samsung^*
Graphics Card Predecessor: GeForce 20^*
Recommended Resolutions: Good:1920x1080 | Low FPS:2560x1440 | Unplayable:3840x2160^*
Board Design Length: 242 mm 9.5 inches^*
Graphics Processor GPU Variant: GA106-400-A1^*
Board Design Power Connectors: 1x 12-pin^*
Graphics Processor Density: 43.5M / mm²^*
Board Design Height: 112 mm 4.4 inches^*
Graphics Card Reviews: 61 in our database^*
Top TMUS: 120^*
Graphics Processor Chip Package: BGA-2713^*
Top ROPS: 48^*
Clock Speeds Base Clock: 1,627^* MHz
Clock Speeds Boost Clock: 1,852^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 3,840^*
Render Config Shading Units: 3,840^*
Render Config L2 Cache: 3^* MB
Top MEMORY SIZE: 6^* GB
Theoretical Performance FP32 (float): 14.22^* TFLOPS
Theoretical Performance FP64 (double): 222.2 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 14.22 TFLOPS (1:1)
Graphics Card Availability: Feb 25th, 2021^*
Top MEMORY TYPE: GDDR6^*
Render Config RT Cores: 30^*

* Provisional data