This row is the 8 GB, 128-bit, 130 W desktop RTX 3050 announced at CES 2022. NVIDIA later sold a 6 GB, 96-bit, 70 W card under the same name, and its own footnote records a third configuration: "GeForce RTX 3050 (OEM) has 2304 CUDA Cores, a Base Clock of 1.51 GHz, and a Boost Clock of 1.76 GHz". Neither of those is this row. Memory bandwidth is not published and is deliberately left blank.

NVIDIA GeForce RTX 3050 8GB

Ampere PCIe 2022 8nm Spec confidence: Vendor claimed
FP32
9.1
TFLOPS
VRAM
8 GB
GDDR6
TDP
130 W
70.0 TFLOPS/kW
Download datasheet

Overview

The GeForce RTX 3050 is the smallest desktop Ampere card that still carries third-generation tensor cores, and it is worth knowing about mainly as a floor: 8 GB of GDDR6 and 130 W make it the cheapest way to get CUDA tensor acceleration into a machine that has no spare power budget. Throughput is 9.1 TFLOPS of FP32 and 18.2 TFLOPS of dense BF16, roughly a seventh of an RTX 3090, so it is a card for small models, embeddings and experimentation rather than training. The GeForce tensor restriction applies here as everywhere in the GeForce RTX 30 line, meaning TF32 matches the shader rate while INT8 and INT4 run at full speed. Watch the name: NVIDIA also ships a 6 GB 70 W card and an OEM variant with fewer cores under the same RTX 3050 badge.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.1TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
9.1TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
9.1TFLOPS 18TFLOPS
BF16
Brain Float 16
18TFLOPS 36TFLOPS
FP16
16-bit floating point
18TFLOPS 36TFLOPS
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
73TOPS 146TOPS
INT4
4-bit integer
146TOPS 291TOPS

The GeForce RTX 3050 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 3050 8GB

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

Specifications

Architecture

Ampere

Form Factor

PCIe

Launch Year

2022

Process Node

8nm

Memory

8 GB GDDR6

Bandwidth

No verified data available

TDP

130 W

Max Power

130 W

CUDA Cores

2,560

Spec Confidence

Vendor claimed

Full Specifications

Compute Engine
CUDA Cores 2,560
Tensor Cores 80 (3rd Gen)
Streaming Multiprocessors 20
Base Clock 1.55 GHz
Boost Clock 1.78 GHz
Memory
VRAM 8 GB
Memory Type GDDR6
Bandwidth No verified data available
Interface Width 128-bit
Interconnect & I/O
PCIe 4.0 x16
Power & Thermal
TDP 130 W
Max Board Power 130 W
Power Connector 1x PCIe 8-pin
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 2022

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

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

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 3050 have?

The NVIDIA GeForce RTX 3050 delivers 9.1 TFLOPS FP32 and 18 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 3050?

The NVIDIA GeForce RTX 3050 has a TDP (Thermal Design Power) rating of 130 watts.

How much memory does the NVIDIA GeForce RTX 3050 have?

The NVIDIA GeForce RTX 3050 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 3050 based on?

The NVIDIA GeForce RTX 3050 is based on the Ampere architecture, launched in 2022.

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