This is the original 6 GB, 192-bit RTX 2060 announced at CES 2019. NVIDIA later sold a 12 GB card under the same name with a different core count and power figure; it is a separate row. NVIDIA published no TFLOPS figure for this card, so its precision ladder is derived from the published core count and boost clock using the TU106 rates the Turing whitepaper prints for the RTX 2070.

NVIDIA GeForce RTX 2060 6GB

Turing PCIe 2019 12nm Spec confidence: Vendor claimed
FP32
6.5
TFLOPS
VRAM
6 GB
GDDR6
Bandwidth
336 GB/s
memory
TDP
160 W
40.3 TFLOPS/kW

Overview

The GeForce RTX 2060 was the cheapest card of its generation with tensor cores, and it remains the floor of the RTX line rather than a serious AI card: 6 GB on a 192-bit bus is enough for small vision models and quantised experiments and little else. Throughput is 6.45 TFLOPS of FP32 and roughly 25.8 TFLOPS of FP16 tensor accumulating in FP32, with 103 TOPS of INT8. Turing has no BF16, no TF32, no FP8 and no structured sparsity, so those figures are dense and comparable as printed. There is no NVLink on TU106. If you are looking at a 2060 for AI work, check whether the listing is this card or the later 12 GB version, which has a third more cores as well as twice the memory.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
64-bit floating point
0.2TFLOPS
FP32
32-bit floating point
6.5TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
16-bit floating point
26TFLOPS
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
8-bit integer
103TOPS
INT4
4-bit integer
206TOPS

Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.

The GeForce RTX 2060 6GB in the GPU landscape

Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper

06001,2001,8002,4003,0000 W250 W500 W750 W1000 W1250 W1500 WInstinct MI355XGeForce RTX 2060 6GB

Higher and further left is better: more half-precision throughput for less power.

Specifications

Architecture

Turing

Form Factor

PCIe

Launch Year

2019

Process Node

12nm

Memory

6 GB GDDR6

Bandwidth

336 GB/s

TDP

160 W

Max Power

160 W

Transistors

10.8 billion

CUDA Cores

1,920

Spec Confidence

Vendor claimed

Full Specifications

Compute Engine
CUDA Cores 1,920
Tensor Cores 240 (Turing)
Streaming Multiprocessors 30
Base Clock 1.36 GHz
Boost Clock 1.68 GHz
Chip Design
Transistors 10.8 billion
Die Size 445 mm²
Process Node 12nm
Memory
VRAM 6 GB
Memory Type GDDR6
Bandwidth 336 GB/s
Interface Width 192-bit
Memory Clock 14 GT/s
Interconnect & I/O
PCIe 3.0 x16
Power & Thermal
TDP 160 W
Max Board Power 160 W
Power Connector 8 pin
Cooling Active
Enterprise Features
ECC Memory No
Sparsity No
Compute APIs CUDA, DirectX 12, Vulkan, OpenGL
Physical & Media
Card Length 228.6 mm
Width 2-slot
General
Form Factor PCIe
Architecture Turing
Process Node 12nm
Launch Year 2019

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2019-01-06

Data Quality

Spec confidence
Vendor claimed
Clock basis
Boost
Core precisions with figures
4 of 9
Normalization
All values in TFLOPS

Rent this GPU

$0.41 / GPU-hr

Lowest of 1 live listing across 1 provider

See all rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Similar GPUs

Frequently Asked Questions

How many TFLOPS does the NVIDIA GeForce RTX 2060 have?

The NVIDIA GeForce RTX 2060 delivers 6.5 TFLOPS FP32 and 26 TFLOPS FP16 at peak. Flopper does not currently have a verified FP8 throughput figure for it.

What is the power consumption of the NVIDIA GeForce RTX 2060?

The NVIDIA GeForce RTX 2060 has a TDP (Thermal Design Power) rating of 160 watts.

How much memory does the NVIDIA GeForce RTX 2060 have?

The NVIDIA GeForce RTX 2060 is equipped with 6 GB of VRAM with 336 GB/s of memory bandwidth.

What architecture is the NVIDIA GeForce RTX 2060 based on?

The NVIDIA GeForce RTX 2060 is based on the Turing architecture, launched in 2019.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs