The RTX 3070 Ti is the full 48-SM GA104 die with GDDR6X in place of the RTX 3070's GDDR6. NVIDIA announced it alongside the RTX 3080 Ti at COMPUTEX on 31 May 2021 but published a TFLOPS headline only for the 3080 Ti, so this row's precision ladder is derived rather than transcribed. Memory bandwidth is not published for this SKU and is deliberately left blank.

NVIDIA GeForce RTX 3070 Ti 8GB

Ampere PCIe 2021 8nm Spec confidence: Vendor claimed
FP32
22
TFLOPS
VRAM
8 GB
GDDR6X
TDP
290 W
75.0 TFLOPS/kW

Overview

The GeForce RTX 3070 Ti is the complete GA104 die, all 48 streaming multiprocessors enabled, paired with GDDR6X instead of the plain GDDR6 on the RTX 3070. For AI work it is a modest step up on paper and a real one in memory-bound inference, but the 8 GB frame buffer is the binding constraint: it is the same 8 GB the RTX 3070 carries, on the same 256-bit bus, and 8 GB is where most useful models stop fitting in half precision. The tensor ladder is the GeForce GA10x one, so TF32 matches the FP32 shader rate rather than doubling it, while INT8 and INT4 run at the full 8x and 16x. At 290 W it draws considerably more than the 220 W RTX 3070 for the extra silicon and the faster memory.

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
22TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
22TFLOPS 44TFLOPS
BF16
Brain Float 16
44TFLOPS 87TFLOPS
FP16
16-bit floating point
44TFLOPS 87TFLOPS
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
174TOPS 348TOPS
INT4
4-bit integer
348TOPS 696TOPS

The GeForce RTX 3070 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 3070 Ti 8GB

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

Specifications

Architecture

Ampere

Form Factor

PCIe

Launch Year

2021

Process Node

8nm

Memory

8 GB GDDR6X

Bandwidth

No verified data available

TDP

290 W

Max Power

290 W

Transistors

17.4 billion

CUDA Cores

6,144

Spec Confidence

Vendor claimed

Full Specifications

Compute Engine
CUDA Cores 6,144
Tensor Cores 192 (3rd Gen)
Streaming Multiprocessors 48
Base Clock 1.58 GHz
Boost Clock 1.77 GHz
Chip Design
Transistors 17.4 billion
Die Size 393 mm²
Process Node 8nm
Memory
VRAM 8 GB
Memory Type GDDR6X
Bandwidth No verified data available
Interface Width 256-bit
Interconnect & I/O
PCIe 4.0 x16
Power & Thermal
TDP 290 W
Max Board Power 290 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 2021

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

$0.07 / 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 3070 Ti have?

The NVIDIA GeForce RTX 3070 Ti delivers 22 TFLOPS FP32 and 44 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 3070 Ti?

The NVIDIA GeForce RTX 3070 Ti has a TDP (Thermal Design Power) rating of 290 watts.

How much memory does the NVIDIA GeForce RTX 3070 Ti have?

The NVIDIA GeForce RTX 3070 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 3070 Ti based on?

The NVIDIA GeForce RTX 3070 Ti is based on the Ampere architecture, launched in 2021.

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