Compute-identical to the 16 GB RTX 5060 Ti. Same GB206 bin, same 2.57 GHz boost, same 448 GB/s, same 180 W. The only difference is the 8 GB frame buffer, which is the whole story for AI use.

NVIDIA GeForce RTX 5060 Ti 8GB

Blackwell PCIe 2025 4nm Spec confidence: Official
FP8 (dense)
190
TFLOPS
FP32
24
TFLOPS
VRAM
8 GB
GDDR7
Bandwidth
448 GB/s
memory
TDP
180 W
131.8 TFLOPS/kW

Overview

The 8 GB GeForce RTX 5060 Ti is the same silicon and the same clocks as the 16 GB card, with half the memory. For gaming that is a modest handicap; for local inference it is decisive, because 8 GB will not hold a 13B model at four bits once you allow for context and the framework's own overhead. Everything else is unchanged: 4,608 Blackwell CUDA cores, 144 fifth-generation Tensor cores, 189.8 TFLOPS of dense FP8, 379.5 TFLOPS of dense FP4, and 448 GB/s across a 128-bit GDDR7 bus. If a rental listing or a retail page says only "RTX 5060 Ti", check which one it is before assuming capacity.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.4TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
24TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
24TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
BF16
Brain Float 16
47TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP16
16-bit floating point
95TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP8
8-bit floating point
190TFLOPS 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
4-bit floating point
380TFLOPS 759TFLOPS
INT8
8-bit integer
190TOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision

The GeForce RTX 5060 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 5060 Ti 8GB

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

Specifications

Architecture

Blackwell

Form Factor

PCIe

Launch Year

2025

Process Node

4nm

Memory

8 GB GDDR7

Bandwidth

448 GB/s

TDP

180 W

Max Power

180 W

CUDA Cores

4,608

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 4,608
Tensor Cores 144 (5th Gen)
Streaming Multiprocessors 36
Base Clock 2.41 GHz
Boost Clock 2.57 GHz
Memory
VRAM 8 GB
Memory Type GDDR7
Bandwidth 448 GB/s
Interface Width 128-bit
Memory Clock 28 GT/s
Interconnect & I/O
PCIe 5.0
Power & Thermal
TDP 180 W
Max Board Power 180 W
Cooling Active
Enterprise Features
Sparsity Yes
General
Form Factor PCIe
Architecture Blackwell
Process Node 4nm
Launch Year 2025

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2025-04-15

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
8 of 9
Normalization
All values in TFLOPS

Rent this GPU

$0.08 / 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 5060 Ti have?

The NVIDIA GeForce RTX 5060 Ti delivers 24 TFLOPS FP32, 95 TFLOPS FP16 and 190 TFLOPS FP8 at peak.

What is the power consumption of the NVIDIA GeForce RTX 5060 Ti?

The NVIDIA GeForce RTX 5060 Ti has a TDP (Thermal Design Power) rating of 180 watts.

How much memory does the NVIDIA GeForce RTX 5060 Ti have?

The NVIDIA GeForce RTX 5060 Ti is equipped with 8 GB of VRAM with 448 GB/s of memory bandwidth.

What architecture is the NVIDIA GeForce RTX 5060 Ti based on?

The NVIDIA GeForce RTX 5060 Ti is based on the Blackwell architecture, launched in 2025.

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