Radeon RX Vega 64 Liquid Cooling

Reference GPU

Save this GPU, then open another GPU page to compare them side by side.

At a Glance

Identity
Entry Type	Reference GPU
Official Name	AMD Radeon RX Vega 64 Liquid Cooling
Architecture	GCN 5.0
Launch Date	2017-08-07
Core Specs
GPU Die	Vega 10
Chip Variant / Package	BGA-2013
Process Node	GlobalFoundries 14 nm
Transistor Count	12.5 billion
Die Size	495 mm²
Stream Processors	4096
TMUs	256
ROPs	64
Base Clock	1,406 MHz
Boost Clock	1,677 MHz
Pixel Fillrate	107.3 GP/s
Texture Fillrate	429.3 GT/s
FP32 Throughput	13.74 TFLOPS
FP16 Throughput	27.48 TFLOPS
FP64 Throughput	0.86 TFLOPS
Memory
Memory Size	8 GB
Memory Type	HBM2
Memory Bus Width	2048-bit
Memory Clock	945 MHz
Memory Bandwidth	483.8 GB/s
L2 Cache	4 MB
L1 Cache	16 KB
Board and Display
TDP / TBP	345 W
Recommended PSU	700 W
Interface	PCIe 3.0 x16
Display Outputs	1x HDMI 2.0b, 3x DisplayPort 1.4a
Slot Width	Dual-slot
Card Length	272 mm
Software
Shader Model	6.7
DirectX Support	DirectX 12.1
Vulkan Support	Vulkan 1.3
OpenGL Support	OpenGL 4.6
OpenCL Support	OpenCL 2.1

This GPU Wiki entry is being expanded and source-checked.

This entry is currently a specification record. Historical notes will be added after source review.

Known issues pending source review.

SourcesPartial

Sources reviewed: 2026-06-23

This entry is still being source-checked.

Data confidence and source status

Partial entry. Core specifications may be present, but history, variant notes, known issues, and source review may be incomplete.

Verified: core specifications and historical notes have been reviewed against listed sources.
Partial: core specifications may be present, but history, variant notes, known issues, and source review may be incomplete.
Imported: spec-only imported entry pending editorial source review.
Needs source review: narrative notes are incomplete until reviewed.

Found an incorrect spec, missing source, or variant issue?

Submit a correction