The abbreviation “Ti” means “Titanium” when seen in an NVIDIA GPU Name. Some examples include the 3080 Ti, 2080 Ti, 1080 Ti.<\/strong><\/p>\n It doesn\u2019t mean, however, that there is any Titanium used in the manufacturing of the GPU. At least not more than in any non-Ti cards.<\/p>\n Now, how does this translate to performance<\/strong><\/a>? Let's take a look at some of the more recent generations of NVIDIA Cards:<\/p>\n As we can see, the Ti Versions have a lot more Shader (CUDA) Cores, more VRAM and tend to designate both higher value and higher performance GPUs in the NVIDIA GPU Generation line-up<\/a> compared to non-Ti GPUs of the same tier.<\/p>\n “Ti”-Version of GPUs are often released at a later date than their non-Ti counterparts. They usually are a means to stay competitive against products AMD releases. In addition, they are often launched to lower prices of certain performance tiers without actually lowering the prices of existing GPUs.<\/p>\n The Ti Version also clearly outranks the non-Ti GPU in Octane-Bench<\/a><\/strong>.<\/p>\n\n
\nGTX 780Ti: CUDA-Cores: 2880, VRAM: 3GB, Octane-Bench: 103<\/strong><\/li>\n<\/ul>\n\n
\nGTX 980Ti: CUDA-Cores: 2816, VRAM: 6GB, Octane-Bench: 137<\/strong><\/li>\n<\/ul>\n\n
\nGTX 1080Ti: CUDA-Cores: 3584, VRAM 11GB, Octane-Bench: 191<\/strong><\/li>\n<\/ul>\n\n
\nRTX 2080Ti: CUDA-Cores: 4352, VRAM: 11GB, Octane-Bench: 348<\/strong><\/li>\n<\/ul>\n\n
\nRTX 3080Ti: CUDA-Cores: 10240, VRAM: 12GB, Octane-Bench: 650<\/strong><\/li>\n<\/ul>\n![\"Relative](\"https:\/\/g100.us\/wp-content\/uploads\/media\/2017\/08\/Relative-Performance.jpg\")