NVIDIA later shipped a GDDR6X version of this card at the same core count and clocks; its own specification page prints the memory row as "8 GB GDDR6 / 8 GB GDDR6X". This row is the original GDDR6 model announced on 1 December 2020. Compute is identical between the two, and NVIDIA publishes no bandwidth figure for either, so the two are not separated here. Memory bandwidth is deliberately left blank rather than derived.

NVIDIA GeForce RTX 3060 Ti 8GB

Ampere PCIe 2020 8nm Spec confidence: Vendor claimed
FP32
16
TFLOPS
VRAM
8 GB
GDDR6
TDP
200 W
81.0 TFLOPS/kW

Overview

The GeForce RTX 3060 Ti was the value inflection point of the Ampere generation, a cut-down GA104 with 38 of the die's 48 streaming multiprocessors that matched the previous flagship RTX 2080 SUPER for 399 dollars. For AI work it is the cheapest Ampere card that still feels quick at INT8 inference, since the GeForce tensor restriction leaves the integer paths at full rate even though it halves TF32. The 8 GB frame buffer is the ceiling, and it is a hard one: it decides what fits, not the throughput. NVIDIA later reissued the card with GDDR6X at identical core counts and clocks, so a listing that does not name the memory type is ambiguous only on bandwidth, never on compute.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.3TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
16TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
16TFLOPS 32TFLOPS
BF16
Brain Float 16
32TFLOPS 65TFLOPS
FP16
16-bit floating point
32TFLOPS 65TFLOPS
FP8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP6
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP4
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
INT8
8-bit integer
130TOPS 259TOPS
INT4
4-bit integer
259TOPS 518TOPS

The GeForce RTX 3060 Ti 8GB 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 3060 Ti 8GB

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

Specifications

Architecture

Ampere

Form Factor

PCIe

Launch Year

2020

Process Node

8nm

Memory

8 GB GDDR6

Bandwidth

No verified data available

TDP

200 W

Max Power

200 W

Transistors

17.4 billion

CUDA Cores

4,864

Spec Confidence

Vendor claimed

Full Specifications

Compute Engine
CUDA Cores 4,864
Tensor Cores 152 (3rd Gen)
Streaming Multiprocessors 38
Base Clock 1.41 GHz
Boost Clock 1.67 GHz
Chip Design
Transistors 17.4 billion
Die Size 393 mm²
Process Node 8nm
Memory
VRAM 8 GB
Memory Type GDDR6
Bandwidth No verified data available
Interface Width 256-bit
Interconnect & I/O
PCIe 4.0 x16
Power & Thermal
TDP 200 W
Max Board Power 200 W
Cooling Active
Enterprise Features
ECC Memory No
Sparsity Yes
Compute APIs CUDA, DirectX 12, Vulkan, OpenGL
General
Form Factor PCIe
Architecture Ampere
Process Node 8nm
Launch Year 2020

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
No verified data available

Data Quality

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

Rent this GPU

$0.05 / 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

NVIDIA RTX A6000 48GB

PCIe · 2020
FP32: 39 TFLOPS
Compare vs RTX A6000

NVIDIA A40 48GB

PCIe · 2021
FP32: 37 TFLOPS
Compare vs A40

NVIDIA A10G 24GB

PCIe · 2022
FP32: 35 TFLOPS
Compare vs A10G

Frequently Asked Questions

How many TFLOPS does the NVIDIA GeForce RTX 3060 Ti have?

The NVIDIA GeForce RTX 3060 Ti delivers 16 TFLOPS FP32 and 32 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 3060 Ti?

The NVIDIA GeForce RTX 3060 Ti has a TDP (Thermal Design Power) rating of 200 watts.

How much memory does the NVIDIA GeForce RTX 3060 Ti have?

The NVIDIA GeForce RTX 3060 Ti is equipped with 8 GB of VRAM. Flopper does not currently have a verified memory bandwidth figure for it.

What architecture is the NVIDIA GeForce RTX 3060 Ti based on?

The NVIDIA GeForce RTX 3060 Ti is based on the Ampere architecture, launched in 2020.

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