GeForce MX550 vs GeForce MX350
VS
Nvidia GeForce MX550
TU117
Nvidia GeForce MX350
GP107
We compared two discrete laptop gaming GPUs: the GeForce MX550 with 8 pipelines and 1024 shaders against the 1 year and 11 months older GeForce MX350 that utilizes 5 pipelines and 640 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
DeviceFacts Final Score
Overall video card score
Key differences
Reasons to consider the GeForce MX550
- Performs significantly better (up to 2.2x) in 3DMark Steel Nomad Lite
- Shows 2x higher average frame rate in modern games at QHD resolution – 14 vs 7 FPS
- 42% higher maximum theoretical performance (2.7 vs 1.9 TFLOPS)
- Manufactured using a more efficient 12 nm process technology
- Achieves 2.5x more points in the GeekBench 6 Compute test (38K vs 15K)
- Has 71% higher memory bandwidth: 96 vs 56 GB/s
- Has 60% more shading units (1024 vs 640)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 28 16 14 - |
12 - - - |
| The Witcher 3 | 25 19 14 - |
- - - - |
| Counter-Strike 2 | 48 29 20 9 |
32 15 12 - |
| Far Cry 6 | 32 29 18 10 |
19 15 10 - |
| Hogwarts Legacy | 20 12 11 - |
14 9 - - |
| CoD: Modern Warfare III | 29 23 16 10 |
27 20 13 9 |
| Ghost of Tsushima | 16 - 9 - |
10 - - - |
| Cyberpunk 2077 | 14 11 - - |
- |
| Shadow of the Tomb Raider | 27 23 16 - |
15 - - - |
| 1080p High | 27 | 16 |
| 1080p Ultra | 19 | 9 |
| 1440p Ultra | 14 | - |
| 4K Ultra | - | - |
| Margin of Error | High | Medium |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 2378 | 1237 |
| Fire Strike | 5959 | 4235 |
| Wild Life Extreme | 5060 | 2693 |
| Night Raid | 29231 | 17004 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 70.9 img/sec | 40 img/sec |
| Face Detection | 37 img/sec | 18.9 img/sec |
| Horizon Detection | 1.28 Gpixels/sec | 0.59 Gpixels/sec |
| Edge Detection | 1.7 Gpixels/sec | 0.88 Gpixels/sec |
| Gaussian Blur | 1.9 Gpixels/sec | 0.97 Gpixels/sec |
| Feature Matching | 0.55 Gpixels/sec | 0.15 Gpixels/sec |
| Stereo Matching | 180.5 Gpixels/sec | 45.1 Gpixels/sec |
| Particle Physics | 5147.2 FPS | 1531.6 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 384 | 238 |
| DirectX 11 | 33 FPS | 20 FPS |
| DirectX 12 | 27 FPS | 15 FPS |
| GPU Compute | 2145 Ops/s | 1251 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 1833 | 949 |
| Image Segmentation (HP) | 3301 | 1407 |
| Image Super Resolution (Q) | 4390 | 2693 |
| Face Detection (HP) | 5360 | 2453 |
| Pose Estimation (Q) | 15739 | 8112 |
| Text Classification (SP) | 1514 | 1170 |
| Machine Translation (HP) | 1827 | 1183 |
| Object Detection (SP) | 2338 | 768 |
| Depth Estimation (Q) | 8861 | 3878 |
| Style Transfer (SP) | 37895 | 20820 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce MX550 and GeForce MX350General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 1, 2022 | February 10, 2020 |
| Case | Laptop | Laptop |
| Purpose | Gaming | Gaming |
| Segment | Entry-level | Entry-level |
| Architecture | Turing | Pascal |
| GPU Codename | TU117 | GP107 |
| Rival Equivalent | - Radeon 760M | - |
| Successor | - | - GeForce MX550 |
| Recommended CPU | - Intel Core i7 1260P or above | - Intel Core i7 1165G7 or above |
Laptop GPU ranking (122nd and 143rd place)
Graphics Processing Unit
| Base Clock | 1065 MHz | 747-1354 MHz (configurable) |
| Boost Clock | 1320 MHz | 936-1468 MHz (configurable) |
| Shading Units | 1024 | 640 |
| Texture Mapping Units (TMUs) | 32 | 32 |
| Render Output Units (ROPs) | 16 | 16 |
| Compute Units (Pipelines) | 8 | 5 |
| Tensor Cores | No | No |
| Ray-tracing Cores | No | No |
| L1 Cache | 128KB per cluster | 48KB per cluster |
| L2 Cache | 2MB shared | 512KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 21 GPixel/s | 15-23 GPixel/s |
| Texture Fill Rate | 42 GTexel/s | 30-47 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 3.0 x4 |
| TGP | 25 W | 15-30 W (configurable) |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 12 nm | 14 nm |
| Die Size | 200 mm² | 132 mm² |
| Transistor Count | 4.7 billion | 3.3 billion |
| Transistor Density | 23.5 MTr/mm² | 25 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR5 |
| Memory Size | 2 GB | 2 GB |
| Memory Clock | 1500 MHz | 1752 MHz |
| Effective Memory Speed | 12000 Mbps | 7000 Mbps |
| Bus | 64-bit | 64-bit |
| ECC | No | - |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.2 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.2 |
| CUDA | 7.5 | 6.1 |
| Ray Tracing | No | No |
| DLSS | No | No |
| DisplayPort | 1.4 | 1.4 |
Cast your vote
Total votes: 1