If everyone thought that NVidia has done it with the GTX1080 as an ultimate graphic card for this year, well they are not. CEO, Jen-Hsun Huang took a bet with one of his hardware engineers that he could get more than 10 teraflops of computing performance from a single chip, and he did.

The Nvidia Titan X is the result of that bet, based on Pascal GPU architecture, the graphic card scores 3584 CUDA cores, a record. Plus it is also armed with 12GB of GDDR5X memory- one of the fastest memory technologies available today.

Here’s the rundown:

• 11 TFLOPS FP32
• 44 TOPS INT8 (new deep learning inferencing instruction)
• 12B transistors
• 3,584 CUDA cores at 1.53GHz (versus 3,072 cores at 1.08GHz in previous TITAN X)
• Up to 60% faster performance than previous TITAN X
• High performance engineering for maximum overclocking
• 12 GB of GDDR5X memory (480 GB/s)

TITAN X will be released on Aug. 2 for $1,200 direct from nvidia.com in North America and Europe, and select system builders. It is coming soon to Asia.