Radeon RX 6600 XT vs Radeon RX Vega 64 Limited Edition
Summary
Reasons to consider Radeon RX 6600 XT |
| 135 watts lower power draw. This might be a strong point if your current power supply is not enough to handle the Radeon RX Vega 64 Limited Edition . |
| This is a much newer product, it might have better long term support. |
| Supports Direct3D 12 Async Compute |
| Supports FreeSync |
| Supports ReLive (allows game streaming/recording with minimum performance penalty) |
| Infinity Cache allows to deliver up to 3.25x the effective memory bandwidth |
| Supports DirectX Raytracing (DXR) |
Reasons to consider Radeon RX Vega 64 Limited Edition |
| Supports Direct3D 12 Async Compute |
| Supports FreeSync |
| Supports ReLive (allows game streaming/recording with minimum performance penalty) |
| Supports TrueAudio |
| Based on an outdated architecture (AMD GCN), there may be no performance optimizations for current games and applications |
No clear winner declared
We have no data to declare a winner at this time.
Core Configuration
| Radeon RX 6600 XT | | Radeon RX Vega 64 Limited Edition | |
|---|
| GPU Name | Navi 23 (Navi 23 XT
(215-130000006)) | vs | Vega 10 (Vega 10 XT) |
| Fab Process | 7 nm | vs | 14 nm |
| Die Size | 237 mm² | vs | 484 mm² |
| Transistors | 11,060 million | vs | 12,500 million |
| Shaders | 2048 | vs | 4096 |
| Raytracing Cores | 32 | vs | none |
| Compute Units | 32 | vs | 64 |
| Core clock | 1968 MHz | vs | 1247 MHz |
| ROPs | 64 | vs | 64 |
| TMUs | 128 | vs | 256 |
Memory Configuration
| Radeon RX 6600 XT | | Radeon RX Vega 64 Limited Edition | |
|---|
| Memory Type | GDDR6 | vs | HBM2 |
| Bus Width | 128 bit | vs | 2048 bit |
| Memory Speed | 2000 MHz
16 Gbps effective | vs | 945 MHz
1890 MHz effective |
| Memory Size | 8192 Mb | vs | 8192 Mb |
Additional details
| Radeon RX 6600 XT | | Radeon RX Vega 64 Limited Edition | |
|---|
| TDP | 160 watts | vs | 295 watts |
| Release Date | 30 Jul 2021 | vs | 8 Aug 2017 |
GigaPixels - higher is better
GigaTexels - higher is better
GFLOPs - higher is better