MSI GeForce RTX 3080 Ti Gaming X Trio Specs
            MSI GeForce RTX 3080 Ti Gaming X Trio
            
                $840
            
        
    | 10240 Shaders 12GB GDDR6X 1770MHz | 
| Peak AI Performance 1.16 POPS INT4 Tensor Sparse | 
| FP32 36.25 TFLOPS | 
| FP16 36.25 TFLOPS | 
| Form Factor PCIe Card 2.8-Slots | 
| TDP 350W | 
| Power Connectors - 3x 8-Pin - - | 
| GB6 OpenCL N/A 0% | 
| GB6 Metal N/A 0% | 
| GB6 Vulkan N/A 0% | 
| GB5 OpenCL 216,210 71% | 
| GB5 CUDA 240,990 68% | 
| GB5 Metal N/A 0% | 
| GB5 Vulkan 145,450 71% | 
| OCT 2020.1 690 91% | 
| OCT Metal N/A 0% | 
| Peak AI
                                            Performance 
                                            1.16 POPS
                                         
                                            INT4 Tensor Sparse
                                         | 
| 
                                            -
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         | 
| 
                                            -
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         | 
| 
                                            FP16
                                         
                                            36.25 TFLOPS
                                            
                                                
                                            
                                         
                                            145 TFLOPS
                                            
                                                 Tensor (FP16 Accumulate)
                                            
                                         
                                            290 TFLOPS
                                            
                                                 Tensor (FP16 Accumulate) Sparse
                                            
                                         
                                            72.5 TFLOPS
                                            
                                                 Tensor (FP32 Accumulate)
                                            
                                         
                                            145 TFLOPS
                                            
                                                 Tensor (FP32 Accumulate) Sparse
                                            
                                         | 
| 
                                            FP32
                                         
                                            36.25 TFLOPS
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         | 
| 
                                            FP64
                                         
                                            570 GFLOPS
                                            
                                                
                                            
                                         
                                            -
                                            
                                                
                                            
                                         | 
| 
                                            BF16
                                         
                                            36.25 TFLOPS
                                            
                                                
                                            
                                         
                                            72.5 TFLOPS
                                            
                                                 Tensor
                                            
                                         
                                            145 TFLOPS
                                            
                                                 Tensor Sparse
                                            
                                         | 
| 
                                            TF32
                                         
                                            36.25 TFLOPS
                                            
                                                 Tensor
                                            
                                         
                                            72.5 TFLOPS
                                            
                                                 Tensor Sparse
                                            
                                         | 
| 
                                            INT4
                                         
                                            579.99 TOPS
                                            
                                                 Tensor
                                            
                                         
                                            1.16 POPS
                                            
                                                 Tensor Sparse
                                            
                                         | 
| 
                                            INT8
                                         
                                            -
                                            
                                                
                                            
                                         
                                            290 TOPS
                                            
                                                 Tensor
                                            
                                         
                                            579.99 TOPS
                                            
                                                 Tensor Sparse
                                            
                                         | 
| 
                                            INT32
                                         
                                            18.13 TOPS
                                            
                                                
                                            
                                         | 
| 
                                            Ray Tracing
                                         
                                            54.7 TOPS
                                         | 
| Pixel
                                            Fillrate 
                                            198.24 GPixel/s
                                         | 
| 
                                            -
                                         
                                            -
                                         | 
| Texture
                                            Fillrate 
                                            566.4 GTexel/s
                                         | 
| ManufacturerMSI | 
| Chip DesignerNVIDIA | 
| ArchitectureAmpere | 
| FamilyGeForce 30 | 
| Codename NV172 GA102 Variant GA102-225-A1 | 
| Market Segment Desktop | 
| Release Date 6/3/2021 | 
| Foundry Samsung - | 
| Fabrication Node 8N - | 
| Die Size 628 mm² - | 
| Transistor Count 28.3 Billion - | 
| Transistor Density 45.04M/mm² - | 
| Form PCIe Card | 
| Shading Units 10240 Shaders - | 
| Texture Mapping Units 320 TMUs | 
| Render Output Units 112 ROPs | 
| Tensor Cores 320 T-Cores | 
| Ray-Tracing Cores 80 RT-Cores | 
| Streaming Multiprocessors 80 SMs | 
| - - | 
| - - | 
| Graphics Processing Clusters 7 GPCs | 
| - - 1395MHz Base 1770MHz | 
| - - | 
| L1 64KB/SM Tex 128KB/SM - - | 
| L2 6MB Shared | 
| - - - | 
| 12GB GDDR6X - | 
| Bus Width 384Bit | 
| Clock 1188MHz Transfer Rate 19GT/s Bandwidth 912GB/s | 
| - - - - - - - - - | 
| TDP 350W | 
| Temp 93°C Max | 
| - - - - - - - - - - - - - - - - - - - - - - - - 3x DisplayPort 1.4 - - - - - - - - - - - 1x HDMI 2.1 - - | 
| Max Resolution 7680x4320 | 
| Max Resolution Refresh Rate 60Hz | 
| Variable Refresh Rate G-Sync FreeSync - | 
| Display Stream Compression (DSC) Supported | 
| Multi Monitor Support 4 | 
| Content Protection HDCP 2.3 | 
| Model NVENC 7 | 
| Codec - - - - - - - - AVC (H.264) HEVC (H.265) - - - - | 
| Model NVDEC 5 | 
| Codec MPEG-1 MPEG-2 MPEG-4 - VC-1 VP8 VP9 - AVC (H.264) HEVC (H.265) - AV1 - - | 
| Direct X 12 Direct 3D 12_2 | 
| OpenGL 4.6 OpenCL 3.0 Vulkan 1.2 | 
| Shader Model 6.6 CUDA 8.6 - - PureVideo HD VP11 VDPAU Feature Set K | 
| - - - 3x Fans | 
| Power Connectors - - - 3x 8-Pin - - - | 
| Slots Required 2.8 PCIe Version 4.0 PCIe Lanes 16 | 
| - - - - | 
| Height 140 mm (5.51 in) Width 324 mm (12.76 in) Depth 56 mm (2.2 in) | 
 
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                             
                                 
                            Copy Link
    
    