The only RTX 50 desktop card that uses GDDR6 rather than GDDR7, which is why its bandwidth is 320 GB/s against the 448 GB/s the 5060 gets from the same 128-bit bus width.

NVIDIA GeForce RTX 5050 8GB

Blackwell PCIe 2025 4nm Spec confidence: Official
FP8 (dense)
105
TFLOPS
FP32
13
TFLOPS
VRAM
8 GB
GDDR6
Bandwidth
320 GB/s
memory
TDP
130 W
101.2 TFLOPS/kW
Download datasheet

Overview

The GeForce RTX 5050 is the entry point to Blackwell on the desktop: 2,560 CUDA cores, 80 fifth-generation Tensor cores, and 8 GB of GDDR6 on a 128-bit bus at 320 GB/s, all inside 130 W from a single PCIe 8-pin connector. It reaches 105.3 TFLOPS of dense FP8 and 210.5 TFLOPS of dense FP4. For AI that is enough to run small quantised models and to learn the tooling, and the low power draw and single connector mean it will go into almost any desktop without a supply upgrade. It is the one RTX 50 card NVIDIA fitted with GDDR6 instead of GDDR7, so it gives up about 29 percent of the bandwidth its 128-bit sibling the RTX 5060 enjoys.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.2TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
13TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
TensorFloat-32
13TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
BF16
Brain Float 16
26TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP16
16-bit floating point
53TFLOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP8
8-bit floating point
105TFLOPS 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
211TFLOPS 421TFLOPS
INT8
8-bit integer
105TOPS The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision

The GeForce RTX 5050 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 5050 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 GDDR6

Bandwidth

320 GB/s

TDP

130 W

Max Power

130 W

CUDA Cores

2,560

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 2,560
Tensor Cores 80 (5th Gen)
Streaming Multiprocessors 20
Base Clock 2.31 GHz
Boost Clock 2.57 GHz
Memory
VRAM 8 GB
Memory Type GDDR6
Bandwidth 320 GB/s
Interface Width 128-bit
Memory Clock 20 GT/s
Interconnect & I/O
PCIe 5.0
Power & Thermal
TDP 130 W
Max Board Power 130 W
Power Connector 1x PCIe 8-pin
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

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
8 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

Frequently Asked Questions

How many TFLOPS does the NVIDIA GeForce RTX 5050 have?

The NVIDIA GeForce RTX 5050 delivers 13 TFLOPS FP32, 53 TFLOPS FP16 and 105 TFLOPS FP8 at peak.

What is the power consumption of the NVIDIA GeForce RTX 5050?

The NVIDIA GeForce RTX 5050 has a TDP (Thermal Design Power) rating of 130 watts.

How much memory does the NVIDIA GeForce RTX 5050 have?

The NVIDIA GeForce RTX 5050 is equipped with 8 GB of VRAM with 320 GB/s of memory bandwidth.

What architecture is the NVIDIA GeForce RTX 5050 based on?

The NVIDIA GeForce RTX 5050 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