MTT S80 VS GeForce RTX 4090
We are comparing the MTT S80 ( Moore Threads ) head-to-head with the GeForce RTX 4090 ( NVIDIA ) . You’ll get the key pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Note: This comparison of MTT S80 vs. GeForce RTX 4090 is based on Comparigon's analysis and is for informational purposes only.
Last Updated: August 20, 2026
KEY DIFFERENCES OF MTT S80 AND GeForce RTX 4090
Here’s how MTT S80 and GeForce RTX 4090 stack up against each other in their most impactful areas. Use these bullets to see at a glance which graphics card excels where.
Reasons to consider the MTT S80
-
Higher bandwidth bus link (PCIe 5.0 x16)
-
Newer PCIe Version (5.0)
Reasons to consider the GeForce RTX 4090
-
357% higher 4K Ultra FPS (105 vs 23)
-
529% higher 1440p Ultra FPS (176 vs 28)
-
384% higher 1080p Ultra FPS (218 vs 45)
-
1513% higher PassMark G3D Mark score (38098 vs 2362)
-
835% higher PassMark GPU Compute score (26273 vs 2809)
SPECIFICATION TABLE COMPARISON OF MTT S80 AND GeForce RTX 4090
Below is the detailed specification table comparing MTT S80 and GeForce RTX 4090.
Note: Highlighted specs mean that GPU wins that spec row.
If neither side is highlighted, it is a tie or there is not enough data for both specs.
| Specification | MTT S80 | GeForce RTX 4090 |
|---|---|---|
|
General Info
|
||
| GPU Name: | MTT S80 | GeForce RTX 4090 |
| GPU Type: | Discrete | Discrete |
| Codename: | Chunxiao | AD102 |
| Vendor: | Moore Threads | NVIDIA |
| Foundry: | TSMC | TSMC |
| Architecture: | MUSA | Ada Lovelace |
| Generation: | MUSA-Chunxiao | GeForce 40 |
| Release Date: | November 11, 2022 | September 20, 2022 |
|
Board Design
|
||
| Bus Interface: | PCIe 5.0 x16 | PCIe 4.0 x16 |
| PCIe Version: | 5.0 | 4.0 |
| PCIe Lanes: | 16 | x16 |
| Process Size: | 12 nm | 5 nm |
| Transistors: | 22 billion | 76.3 billion |
| Density: | — | 125.29 MTr/mm² |
| Die Size: | — | 609 |
| Board Length: | 285 mm | 304 mm |
| Board Width: | 49 mm | 61 mm |
| Board Height: | 112 mm | 137 mm |
| Total Graphics Power (TGP): | 255 W | 450 W |
|
Graphics Processor
|
||
| Compute Units: | 32 | 128 |
| Shading Units: | 4096 | 16384 |
| Texture Mapping Units (TMUs): | 256 | 512 |
| Render Output Units (ROPs): | 256 | 176 |
| Tensor Cores: | — | 512 |
| Ray Tracing Cores: | — | 128 |
| Base Clock: | 1800 MHz | 2235 |
| Boost Clock: | — | 2520 |
| L1 Cache: | — | 128KB per cluster |
| L2 Cache: | 4 MB | 72MB shared |
|
Raw Performance
|
||
| Pixel Fill Rate: | 460.8 GPixel/s | 443.5 GPixel/s |
| Texture Fill Rate: | 460.8 GTexel/s | 1,290.2 GTexel/s |
| FP32 Performance: | 14.75 TFLOPs | 82.58 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6X |
| Memory Size: | 16 GB | 24 GB |
| Memory Bus Width: | 256-bit | 384-bit |
| Memory Clock: | 1750 MHz | 2625 |
| Effective Memory Speed: | 14000 Mbps | 21000 |
| Bandwidth: | 448 GB/s | 1010 |
|
APIs
|
||
| DirectX: | 12 Ultimate (12.2) | 12 |
| Vulkan: | 1.4 | 1.3 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 3.0 |
| CUDA: | — | 8.9 |
| Ray Tracing: | 1 | Yes |
| DLSS: | — | DLSS 3 |
| DisplayPort: | 1.4a | 1.4a |
| HDMI: | 2.1 | — |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 45 | 218 |
| 1440p Ultra (FPS): | 28 | 176 |
| 4K Ultra (FPS): | 23 | 105 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | — | 42154 |
| Time Spy | — | 36315 |
| Solar Bay | — | 187290 |
| Port Royal | — | 26128 |
| Fire Strike | 7184 | 72272 |
| Wild Life Extreme | — | 85225 |
| Night Raid | — | 195744 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | — | 316301 |
| Background Blur | — | 318.9 img/sec |
| Face Detection | — | 222.8 img/sec |
| Horizon Detection | — | 14.2 Gpixels/sec |
| Edge Detection | — | 21 Gpixels/sec |
| Gaussian Blur | — | 23.9 Gpixels/sec |
| Feature Matching | — | 2.38 Gpixels/sec |
| Stereo Matching | — | 1950 Gpixels/sec |
| Particle Physics | — | 48090.4 FPS |
|
Passmark Graphics
|
||
| G3D Mark | 2362 | 38098 |
| G2D Mark | 634 | 1303 |
| DirectX 11 | 22 | 324 |
| DirectX 12 | 15 | 151 |
| GPU Compute | 2809 | 26273 Ops/s |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | — | 615.90 |
| Aztec Ruins Normal | — | 1617.60 |
| Car Chase | — | 1228.60 |
| Manhattan 3.1.1 (1440p) | — | 1234.60 |
| T-Rex | — | 6286.00 |
| Tessellation | — | 12119.10 |
| ALU 2 | — | 15073.40 |
| Driver Overhead 2 | — | 303.70 |
| API | — | OpenGL |
| OS | — | Windows |
|
Blender (Rendering)
|
||
| Blender Score | — | 11795 |
|
GeekBench 6 ML
|
||
| Single Precision | — | 42962 |
| Half Precision | — | 59636 |
| Quantized | — | 31670 |
| Image Classification | — | 15600 |
| Image Segmentation | — | 36657 |
| Image Super Resolution | — | 48114 |
| Face Detection | — | 78111 |
| Pose Estimation | — | 289639 |
| Text Classification | — | 4074 |
| Machine Translation | — | 6349 |
| Object Detection | — | 21186 |
| Depth Estimation | — | 75599 |
| Style Transfer | — | 601428 |
| Framework | — | ONNX |
| Backend | — | DirectML |
|
FurMark
|
||
| 1080p Vulkan | — | 27475 |
| 1440p Vulkan | — | 20403 |
| 2160p Vulkan | — | 11883 |
| 1080p OpenGL | 2716 | 24851 |
| 1440p OpenGL | 1740 | 19078 |
| 2160p OpenGL | 1405 | 11425 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF MTT S80 AND GeForce RTX 4090
The charts below visualize how MTT S80 and GeForce RTX 4090 stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Release Timeline of MTT S80 and GeForce RTX 4090
GeForce RTX 4090 was released 1 month, 22 days earlier than MTT S80.
Value For Money Calculator
Prices use available launch or current data. Enter your own prices to see which GPU gives better value.
MTT S80
GeForce RTX 4090
Calculating...
Domain Score Summary
Note: Scores (0 to 100) are generated by Comparigon’s scoring algorithm and are intended as a high-level guide. They may not map 1-to-1 with the individual spec-by-spec comparisons shown in the table.
Our Verdict
In conclusion, the GeForce RTX 4090 dominates overall compared to the MTT S80. It comes out ahead across every comparable key area.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.