Radeon 660M vs Radeon Pro 5300M
Review
Key differences
Key distinctions and advantages between Radeon 660M and Radeon Pro 5300M
Reasons to consider the Radeon 660M
- + RDNA 2.0 architecture
- + Rembrandt codename
- + System Shared memory
- + PCIe 4.0 x8 interface
Reasons to consider the Radeon Pro 5300M
- + RDNA 1.0 architecture
- + Navi 14 codename
- + 4GB GDDR6 memory
- + PCIe 4.0 x8 interface
Pros & Cons
- Great energy efficiency
- Hardware ray tracing support
- No discrete card needed — integrated solution
- Limited gaming performance at higher resolutions
"A budget AMD Radeon 660M integrated graphics with limited performance overall, excellent energy efficiency. Suited for casual gaming and basic graphics tasks."
- Dedicated AI tensor cores
- Limited gaming performance at higher resolutions
- No hardware ray tracing
- No DLSS upscaling support
- Older generation architecture
"A budget AMD Radeon Pro 5300M graphics card with limited performance overall. Suited for casual gaming and basic graphics tasks."
Gaming Performance
Forza Horizon 5
The Witcher 3
Counter-Strike 2
Far Cry 6
Hogwarts Legacy
Call of Duty
Ghost of Tsushima
Cyberpunk 2077
Tomb Raider
| Radeon 660M | Radeon Pro 5300M | |||||||
|---|---|---|---|---|---|---|---|---|
| 1080p High | 1080p Ultra | 1440p Ultra | 4K Ultra | 1080p High | 1080p Ultra | 1440p Ultra | 4K Ultra | |
| Forza Horizon 5 | 12 | — | — | — | — | — | — | — |
| The Witcher 3 | 10 | — | — | — | — | — | — | — |
| Counter-Strike 2 | 20 | — | — | — | — | — | — | — |
| Far Cry 6 | 19 | — | — | — | — | — | — | — |
| Call of Duty | 15 | — | — | — | — | — | — | — |
| Ghost of Tsushima | 9 | — | — | — | — | — | — | — |
| Cyberpunk 2077 | 9 | — | — | — | — | — | — | — |
| Tomb Raider | 13 | — | — | — | — | — | — | — |
| Average FPS | 13 | — | — | — | — | — | — | — |
| Radeon 660M | Radeon Pro 5300M | |
|---|---|---|
| 1080p High | 17 | — |
| 1080p Ultra | 13 | — |
| 1440p Ultra | 9 | — |
| 4K Ultra | - | — |
| Margin of Error | Low | — |
Benchmarks
| Radeon 660M | Radeon Pro 5300M | |
|---|---|---|
| Time Spy | 1515 | 3404 |
| Solar Bay | 6396 | — |
| Port Royal | 586 | — |
| Fire Strike | 4870 | — |
| Wild Life Extreme | 2676 | — |
| Night Raid | 19259 | — |
| Radeon 660M | Radeon Pro 5300M | |
|---|---|---|
| G2D Mark | 645 | 559 |
| DirectX 11 | 54 FPS | 36 FPS |
| DirectX 12 | 27 FPS | 25 FPS |
| GPU Compute | 1418 Ops/s | 2580 Ops/s |
Specifications
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| GB6 Compute Score | 14065 | 27065 |
| Background Blur | 36 img/sec | 59.6 img/sec |
| Face Detection | 16.4 img/sec | 34.3 img/sec |
| Horizon Detection | 0.48 Gpixels/sec | 1.19 Gpixels/sec |
| Edge Detection | 0.65 Gpixels/sec | 1.56 Gpixels/sec |
| Gaussian Blur | 0.53 Gpixels/sec | 1.31 Gpixels/sec |
| Feature Matching | 0.18 Gpixels/sec | 0.28 Gpixels/sec |
| Stereo Matching | 46.5 Gpixels/sec | 95.4 Gpixels/sec |
| Particle Physics | 2056.5 FPS | 2473.3 FPS |
| API | OpenCL | OpenCL |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| GB6 ML Single Precision | 3903 | 3321 |
| GB6 ML Half Precision | 4745 | 3307 |
| GB6 ML Quantized | 2977 | 1043 |
| Image Classification (SP) | 1465 | 2457 |
| Image Segmentation (HP) | 1706 | 394 |
| Image Super Resolution (Q) | 4266 | 6055 |
| Face Detection (HP) | 5115 | 9021 |
| Pose Estimation (Q) | 12992 | 2239 |
| Text Classification (SP) | 1116 | 344 |
| Machine Translation (HP) | 1859 | 458 |
| Object Detection (SP) | 1574 | 2523 |
| Depth Estimation (Q) | 6538 | 10775 |
| Style Transfer (SP) | 26656 | 30282 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| Vendor | Amd | Amd |
| Build | Integrated | Discrete |
| Released | 1-Jan-22 | 13-Nov-19 |
| Case | Laptop | Laptop |
| Purpose | Generic | Gaming |
| Segment | Entry-level | Mid-range |
| Architecture | RDNA 2.0 | RDNA 1.0 |
| GPU Codename | Rembrandt | Navi 14 |
| Recommended CPU | -AMD Ryzen 5 6600Hor above |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| Base Clock | 400 MHz | 1000 MHz |
| Boost Clock | 1800-1900 MHz (configurable) | 1250 MHz |
| Shading Units | 384 | 1280 |
| Texture Mapping Units (TMUs) | 24 | 80 |
| Render Output Units (ROPs) | 16 | 32 |
| Compute Units (Pipelines) | 6 | 20 |
| Tensor Cores | No | |
| Ray-tracing Cores | 6 | No |
| L1 Cache | 128KB per cluster | |
| L2 Cache | 1024KB shared | 2MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| Pixel Fill Rate | 29-30 GPixel/s | 40 GPixel/s |
| Texture Fill Rate | 43-46 GTexel/s | 100 GTexel/s |
| FLOPS (FP32) | 1.4-1.5 TFLOPS | 3.2 TFLOPS |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| Interface | PCIe 4.0 x8 | PCIe 4.0 x8 |
| TGP | 15 W | 85 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 6 nm | 7 nm |
| Die Size | 208 mm² | 158 mm² |
| Transistor Count | 13.1 billion | 6.4 billion |
| Transistor Density | 62.98 MTr/mm² | 40.51 MTr/mm² |
| Max. Temperature |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| Memory Type | System Shared | GDDR6 |
| Specification | Radeon 660M ↗ | Radeon Pro 5300M ↗ |
|---|---|---|
| DirectX | 12 | 12 |
| Vulkan | 1.2 | 1.2 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2 | 2.1 |
| CUDA | ||
| Ray Tracing | Yes | No |
| DLSS | No | No |
| DisplayPort | 1.4 |
