AMD Radeon 860M vs Adreno X2-90
AMD Radeon 860M
Krackan Point
Adreno X2-90
Adreno X2
We compared two integrated laptop GPUs: the Radeon 860M with 8 pipelines and 512 shaders against the 9 months newer Adreno X2-90 that utilizes 12 pipelines and 2048 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
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Key differences
Reasons to consider the Adreno X2-90
- Performs significantly better (up to 2.3x) in 3DMark Steel Nomad Lite
- 2.5x higher maximum theoretical performance (7.6 vs 3.1 TFLOPS)
- Manufactured using a more efficient 3 nm process technology
- Has 4x more shading units (2048 vs 512)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 41 24 20 11 |
- |
| The Witcher 3 | 19 18 11 - |
- |
| Counter-Strike 2 | 39 26 19 9 |
- |
| Far Cry 6 | 31 26 16 9 |
- |
| Hogwarts Legacy | 16 12 10 - |
- |
| CoD: Modern Warfare III | 28 27 17 12 |
- |
| Ghost of Tsushima | 16 12 9 - |
- |
| Cyberpunk 2077 | 19 13 - - |
- |
| Shadow of the Tomb Raider | 29 22 15 - |
- |
| 1080p High | 26 | - |
| 1080p Ultra | 20 | - |
| 1440p Ultra | 14 | - |
| 4K Ultra | - | - |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 2604 | 3782 |
| Solar Bay | 11094 | 24300 |
| Port Royal | 1046 | 1592 |
| Fire Strike | 6772 | 10039 |
| Wild Life Extreme | 5124 | 9890 |
| Night Raid | 29064 | 57486 |
GeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | 57.2 img/sec | - |
| Face Detection | 30.5 img/sec | - |
| Horizon Detection | 0.83 Gpixels/sec | - |
| Edge Detection | 1.16 Gpixels/sec | - |
| Gaussian Blur | 0.93 Gpixels/sec | - |
| Feature Matching | 0.35 Gpixels/sec | - |
| Stereo Matching | 97.8 Gpixels/sec | - |
| Particle Physics | 3933.5 FPS | - |
| API | OpenCL | - |
Passmark Graphics
G3D Mark Score
| G2D Mark | 918 | 592 |
| DirectX 11 | 37 FPS | 57 FPS |
| DirectX 12 | 25 FPS | 29 FPS |
| GPU Compute | 2434 Ops/s | 3638 Ops/s |
Recent User Tests
Radeon 860M
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-08-17 (flauzwerfer) | Geekbench 6 OpenCL | 24017 |
| 📘 2026-08-17 (flauzwerfer) | Steel Nomad Light | 2476 |
| 📘 2026-07-04 -> Starjack36 | Geekbench 6 OpenCL | 24971 |
Adreno X2-90
No benchmark results yet
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) | 2022 | - |
| Image Segmentation (HP) | 3987 | - |
| Image Super Resolution (Q) | 6657 | - |
| Face Detection (HP) | 10337 | - |
| Pose Estimation (Q) | 28437 | - |
| Text Classification (SP) | 2326 | - |
| Machine Translation (HP) | 4011 | - |
| Object Detection (SP) | 1995 | - |
| Depth Estimation (Q) | 12031 | - |
| Style Transfer (SP) | 56710 | - |
| Framework | ONNX | - |
| Backend | DirectML | - |
Specifications
Technical specifications of Radeon 860M and Adreno X2-90General
| Vendor | Amd | Qualcomm |
| Build | Integrated | Integrated |
| Released | January 7, 2025 | September 25, 2025 |
| Case | Laptop | Laptop |
| Purpose | Generic | Generic |
| Segment | Mid-range | Mid-range |
| Architecture | RDNA 3.5 | Adreno X2 |
| GPU Codename | Krackan Point | Adreno X2 |
| Rival Equivalent | - Intel Arc 140T | - Apple M4 Max GPU (40-core) |
| Successor | - Radeon 8040S | - |
| Recommended CPU | - AMD Ryzen AI 7 350 or above | - Qualcomm Snapdragon X2 Elite Extreme (X2E-96-100) or above |
| Used in CPUs | - AMD Ryzen AI 7 450 - AMD Ryzen AI 7 350 |
- Qualcomm Snapdragon X2 Elite (X2E-90-100) - Qualcomm Snapdragon X2 Elite (X2E-88-100) - Qualcomm Snapdragon X2 Elite Extreme (X2E-94-100) - Qualcomm Snapdragon X2 Elite Extreme (X2E-96-100) |
Laptop GPU ranking (99th and 34th place)
Graphics Processing Unit
| Base Clock | 600 MHz | 500 MHz |
| Boost Clock | 3000 MHz | 1700-1850 MHz (configurable) |
| Shading Units | 512 | 2048 |
| Texture Mapping Units (TMUs) | 32 | 128 |
| Render Output Units (ROPs) | 16 | 64 |
| Compute Units (Pipelines) | 8 | 12 |
| Tensor Cores | No | No |
| Ray-tracing Cores | 8 | - |
| L1 Cache | 128KB per cluster | - |
| L2 Cache | 2MB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 48 GPixel/s | 109-118 GPixel/s |
| Texture Fill Rate | 96 GTexel/s | 218-237 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | IGP |
| TGP | 15 W | - |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 3 nm |
| Die Size | 233 mm² | 220 mm² |
| Transistor Count | 34 billion | - |
| Transistor Density | 145.92 MTr/mm² | - |
| Max. Temperature | 100°C | - |
Memory
| Memory Type | System Shared | System Shared |
| Bus | - | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12.2 |
| Vulkan | 1.4 | 1.4 |
| OpenGL | 4.6 | - |
| OpenCL | 2.1 | 3.0 |
| CUDA | No | No |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | 1.4 |
Cast your vote
Total votes: < 1