RDNA 2 has no matrix cores. AMD's 17.86 TFLOPS is packed FP16 vector math at exactly twice the FP32 vector rate. AMD publishes no INT8, INT4, BF16, FP8 or FP64 number for this card. Same 28 compute units and 1,792 stream processors as the Radeon PRO W6600, which is clocked higher and reaches 10.4 TFLOPS FP32; the two are the same Navi 23 silicon in different bins.

AMD Radeon RX 6600 8GB

RDNA 2 PCIe 2021 7nm Spec confidence: Official
FP32
8.9
TFLOPS
VRAM
8 GB
GDDR6
Bandwidth
224 GB/s
memory
TDP
132 W
67.7 TFLOPS/kW
Download datasheet

Overview

The Radeon RX 6600 is the entry point of AMD's RDNA 2 desktop range, a 28 compute unit Navi 23 with 8 GB of GDDR6 at 224 GB/s and a 132 W board power that needs only a single eight-pin connector. It is the same die and the same core count as the workstation Radeon PRO W6600, which runs faster and adds professional certification. As with every RDNA 2 part, there are no matrix cores: 8.93 TFLOPS FP32 and a packed 17.86 TFLOPS FP16 at exactly twice that rate is the whole published ladder, with no BF16, FP8, INT8 or INT4 figure anywhere. At 8 GB it is a display card that can run small models, not an inference accelerator.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
8.9TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
16-bit floating point
18TFLOPS
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
No verified data available

Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.

The Radeon RX 6600 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 MI355XRadeon RX 6600 8GB

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

Specifications

Architecture

RDNA 2

Form Factor

PCIe

Launch Year

2021

Process Node

7nm

Memory

8 GB GDDR6

Bandwidth

224 GB/s

TDP

132 W

Max Power

~152 W

Transistors

11.1 billion

Stream Processors

1,792

Spec Confidence

Official

Full Specifications

Compute Engine
Stream Processors 1,792
Compute Units 28
Boost Clock 2.49 GHz
Chip Design
Transistors 11.1 billion
Process Node 7nm
Chiplets 1 (Monolithic)
Memory
VRAM 8 GB
Memory Type GDDR6
Bandwidth 224 GB/s
Interface Width 128-bit
Memory Clock 14 GT/s
Cache
Infinity Cache 32 MB
Power & Thermal
TDP 132 W
Max Board Power The vendor publishes no maximum board power; the Max Power tile above estimates it from TDP
Power Connector 1x8-Pin
Enterprise Features
Sparsity No
Compute APIs DirectX 12, OpenGL, OpenCL, Vulkan
General
Form Factor PCIe
Architecture RDNA 2
Process Node 7nm
Launch Year 2021

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
AMD
Published
No verified data available

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
2 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 AMD Radeon RX 6600 have?

The AMD Radeon RX 6600 delivers 8.9 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 AMD Radeon RX 6600?

The AMD Radeon RX 6600 has a TDP (Thermal Design Power) rating of 132 watts.

How much memory does the AMD Radeon RX 6600 have?

The AMD Radeon RX 6600 is equipped with 8 GB of VRAM with 224 GB/s of memory bandwidth.

What architecture is the AMD Radeon RX 6600 based on?

The AMD Radeon RX 6600 is based on the RDNA 2 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