AMD publishes no double precision figure for this card. Vega 10 runs FP64 at a fraction of its FP32 rate but AMD never printed a number on the product page, so none is recorded. AMD also prints no lithography row for it, so the process node is refused; the die is the same Vega 10 used in the Radeon Instinct MI25. Vega has no matrix cores, so the 25.3 TFLOPS FP16 is Rapid Packed Math on the vector units at twice FP32. amd.com has removed the product page, so the source is a dated Wayback capture of AMD's own page.

AMD Radeon RX Vega 64 8GB

Vega PCIe 2017 Spec confidence: Official
FP32
13
TFLOPS
VRAM
8 GB
HBM2
Bandwidth
484 GB/s
memory
TDP
295 W
43.1 TFLOPS/kW
Download datasheet

Overview

The Radeon RX Vega 64 was AMD's 2017 flagship and the first consumer card to pair HBM2 with a big GCN part: 64 compute units, 4,096 stream processors and 8 GB of HBM2 on a 2048-bit interface at 483.8 GB/s, inside a 295 W board. It is in this catalog as a tier-three historical reference rather than a recommendation, because 8 GB is too small for most modern local inference and 295 W buys only 12.7 TFLOPS of FP32. Its one architectural contribution that still matters is Rapid Packed Math, the feature that doubled FP16 throughput to 25.3 TFLOPS on the vector units; Vega has no matrix cores, so that packed rate is the ceiling and no BF16, FP8, INT8 or INT4 figure exists.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
13TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
16-bit floating point
25TFLOPS
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 Vega 64 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 Vega 64 8GB

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

Specifications

Architecture

Vega

Form Factor

PCIe

Launch Year

2017

Process Node

No verified data available

Memory

8 GB HBM2

Bandwidth

483.8 GB/s

TDP

295 W

Max Power

~339 W

Transistors

12.5 billion

Stream Processors

4,096

Spec Confidence

Official

Full Specifications

Compute Engine
Stream Processors 4,096
Compute Units 64
Base Clock 1.25 GHz
Boost Clock 1.55 GHz
Chip Design
Transistors 12.5 billion
Chiplets 1 (Monolithic)
Memory
VRAM 8 GB
Memory Type HBM2
Bandwidth 484 GB/s
Interface Width 2048-bit
HBM Stacks 2
Memory Clock 1.89 GT/s
Power & Thermal
TDP 295 W
Max Board Power The vendor publishes no maximum board power; the Max Power tile above estimates it from TDP
Enterprise Features
Sparsity No
Compute APIs DirectX 12, OpenGL, OpenCL, Vulkan
General
Form Factor PCIe
Architecture Vega
Process Node No verified data available
Launch Year 2017

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
AMD
Published
2018-11-09

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 Vega 64 have?

The AMD Radeon RX Vega 64 delivers 13 TFLOPS FP32 and 25 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 Vega 64?

The AMD Radeon RX Vega 64 has a TDP (Thermal Design Power) rating of 295 watts.

How much memory does the AMD Radeon RX Vega 64 have?

The AMD Radeon RX Vega 64 is equipped with 8 GB of VRAM with 483.8 GB/s of memory bandwidth.

What architecture is the AMD Radeon RX Vega 64 based on?

The AMD Radeon RX Vega 64 is based on the Vega architecture, launched in 2017.

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