Intel Arc B580 vs GeForce RTX 3050
VS
Intel Arc B580
BMG-G21
Nvidia GeForce RTX 3050
GA106
We compared two discrete desktop gaming GPUs: the Intel Arc B580 12 GB with 20 pipelines and 2560 shaders against the 2 years and 10 months older GeForce RTX 3050 8 GB that utilizes 20 pipelines and 2560 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
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the Intel Arc B580
- Performs significantly better (up to 76%) in 3DMark Steel Nomad Lite
- Shows 60% higher average frame rate in modern games at QHD resolution – 67 vs 42 FPS
- Manufactured using a more efficient 5 nm process technology
- 51% higher maximum theoretical performance (13.7 vs 9.1 TFLOPS)
- Includes 4 GB more video memory
- Features 80 more tensor cores for effective ML and AI workloads
- Has 2x higher memory bandwidth: 456 vs 224 GB/s
- Achieves 66% more points in the GeekBench 6 Compute test (111K vs 67K)
Reasons to consider the GeForce RTX 3050
- Supports Nvidia DLSS 2 technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 123 78 67 51 |
92 53 43 26 |
| The Witcher 3 | 147 128 91 46 |
90 70 49 24 |
| Counter-Strike 2 | 162 116 83 40 |
139 101 72 31 |
| Far Cry 6 | 108 98 76 43 |
76 66 49 25 |
| Hogwarts Legacy | 71 57 44 26 |
49 38 30 13 |
| CoD: Modern Warfare III | 82 85 61 38 |
59 49 35 22 |
| Ghost of Tsushima | 72 61 42 25 |
46 35 28 15 |
| Cyberpunk 2077 | 90 82 55 26 |
48 45 26 11 |
| Shadow of the Tomb Raider | 124 107 83 43 |
80 73 49 25 |
| 1080p High | 109 | 75 |
| 1080p Ultra | 90 | 59 |
| 1440p Ultra | 67 | 42 |
| 4K Ultra | 38 | 21 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 14685 | 6235 |
| Solar Bay | 55846 | 30191 |
| Port Royal | 7939 | 3546 |
| Fire Strike | 36801 | 15967 |
| Wild Life Extreme | 28331 | 12795 |
| Night Raid | 125066 | 74854 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 284.6 img/sec | 110.4 img/sec |
| Face Detection | 150 img/sec | 64.4 img/sec |
| Horizon Detection | 2.67 Gpixels/sec | 2.87 Gpixels/sec |
| Edge Detection | 5.22 Gpixels/sec | 3.76 Gpixels/sec |
| Gaussian Blur | 6.35 Gpixels/sec | 2.89 Gpixels/sec |
| Feature Matching | 1.18 Gpixels/sec | 0.81 Gpixels/sec |
| Stereo Matching | 397 Gpixels/sec | 270.9 Gpixels/sec |
| Particle Physics | 15177.3 FPS | 9339.7 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 702 | 916 |
| DirectX 11 | 125 FPS | 90 FPS |
| DirectX 12 | 78 FPS | 59 FPS |
| GPU Compute | 8018 Ops/s | 6415 Ops/s |
Blender
Blender GPU
Recent User Tests
Intel Arc B580
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-07-07 (Mike) | Geekbench 6 OpenCL | 113977 |
| 📘 2026-07-07 (Mike) | Steel Nomad Light | 11944 |
| 📘 2026-06-17 (Mike) | Geekbench 6 OpenCL | 103868 |
GeForce RTX 3050
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-04-21 -> DmitryDmitry | Cinebench 2024 | 4722 |
| 📘 2026-04-21 -> DmitryDmitry | Steel Nomad Light | 6237 |
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) | 10654 | 4958 |
| Image Segmentation (HP) | 18608 | 12747 |
| Image Super Resolution (Q) | 16715 | 9816 |
| Face Detection (HP) | 40348 | 22467 |
| Pose Estimation (Q) | 64494 | 41362 |
| Text Classification (SP) | 3091 | 2563 |
| Machine Translation (HP) | 3530 | 3721 |
| Object Detection (SP) | 13690 | 5929 |
| Depth Estimation (Q) | 36797 | 18361 |
| Style Transfer (SP) | 197057 | 84665 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Intel Arc B580 and GeForce RTX 3050General
| Vendor | Intel | Nvidia |
| Build | Discrete | Discrete |
| Released | December 3, 2024 | January 27, 2022 |
| Launch price (MSRP) | $249 | $249 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | Entry-level |
| Architecture | Generation 12.7 | Ampere |
| GPU Codename | BMG-G21 | GA106 |
| Rival Equivalent | - GeForce RTX 4060 | - |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i5 12400 or above |
Desktop GPU rating (50th and 71st place)
Graphics Processing Unit
| Base Clock | 1700 MHz | 1552 MHz |
| Boost Clock | 2670 MHz | 1777 MHz |
| Shading Units | 2560 | 2560 |
| Texture Mapping Units (TMUs) | 160 | 80 |
| Render Output Units (ROPs) | 80 | 32 |
| Compute Units (Pipelines) | 20 | 20 |
| Tensor Cores | 160 | 80 |
| Ray-tracing Cores | 20 | 20 |
| L1 Cache | 256KB per cluster | 128KB per cluster |
| L2 Cache | 12MB shared | 2MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 214 GPixel/s | 57 GPixel/s |
| Texture Fill Rate | 427 GTexel/s | 142 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 4.0 x8 |
| TGP | 190 W | 130 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 5 nm | 8 nm |
| Die Size | 272 mm² | 276 mm² |
| Transistor Count | 19.6 billion | 12 billion |
| Transistor Density | 72.06 MTr/mm² | 43.48 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 12 GB | 8 GB |
| Memory Clock | 2375 MHz | 1750 MHz |
| Effective Memory Speed | 19000 Mbps | 14000 Mbps |
| Bus | 192-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | No | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 2 |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 20