RDNA 2 has no matrix cores. AMD's 22.58 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. AMD lists two memory speeds for this board, up to 16 Gbps and up to 14 Gbps; the 320 GB/s bandwidth figure it publishes corresponds to the 16 Gbps configuration and is what is stored here.

AMD Radeon RX 6700 10GB

RDNA 2 PCIe 2021 7nm Spec confidence: Official
FP32
11
TFLOPS
VRAM
10 GB
GDDR6
Bandwidth
320 GB/s
memory
TDP
175 W
64.5 TFLOPS/kW
Download datasheet

Overview

The Radeon RX 6700 without the XT suffix is the quiet member of the Navi 22 family, a 36 compute unit part with 10 GB across a 160-bit bus and 80 MB of Infinity Cache, at 175 W. It never got the launch attention its XT sibling did and reached shelves unevenly, but AMD lists it as a full product with a 6 June 2021 launch date. The unusual 10 GB capacity is the reason to care: it sits between the 8 GB and 12 GB tiers at a low power draw. RDNA 2 has no matrix cores, so 11.29 TFLOPS FP32 and a packed 22.58 TFLOPS FP16 are the full published ladder.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
11TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
16-bit floating point
23TFLOPS
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 6700 10GB 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 6700 10GB

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

10 GB GDDR6

Bandwidth

320 GB/s

TDP

175 W

Max Power

~201 W

Transistors

17.2 billion

Stream Processors

2,304

Spec Confidence

Official

Full Specifications

Compute Engine
Stream Processors 2,304
Compute Units 36
Base Clock 1.94 GHz
Boost Clock 2.45 GHz
Chip Design
Transistors 17.2 billion
Process Node 7nm
Chiplets 1 (Monolithic)
Memory
VRAM 10 GB
Memory Type GDDR6
Bandwidth 320 GB/s
Interface Width 160-bit
Effective Bandwidth 1.1 TB/s
Memory Clock 16 GT/s
Cache
Infinity Cache 80 MB
Power & Thermal
TDP 175 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
Physical & Media
Card Length 267 mm
Width 2-slot
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 6700 have?

The AMD Radeon RX 6700 delivers 11 TFLOPS FP32 and 23 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 6700?

The AMD Radeon RX 6700 has a TDP (Thermal Design Power) rating of 175 watts.

How much memory does the AMD Radeon RX 6700 have?

The AMD Radeon RX 6700 is equipped with 10 GB of VRAM with 320 GB/s of memory bandwidth.

What architecture is the AMD Radeon RX 6700 based on?

The AMD Radeon RX 6700 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