Nvidia has announced the RTX 3070, a $499 graphics card that is faster than a 2080 Ti for far less cash.
With 20 shader TFLOPS, 40 RT TFLOPS, and 163 Tensor TFLOPS, the RTX 3070 is specced for high-end gaming. That’s courtesy of the Ampere graphics architecture, and a whopping 5,888 CUDA cores. It’s also equipped with 8GB of GDDR6 memory.
That’s a touch less than the RTX 2080 Ti, which comes with 11GB of GDDR6 memory. However, according to Nvidia, that won’t hamper its performance. The chipmaker reports performance somewhere in the ballpark of the RTX 2080 Ti, and significantly faster than the RTX 2080 and RTX 2080 Super.
You can check out the full RTX 3070 design above.
Graphics Card Name | RTX 3090 | RTX 3080 | RTX 3070 |
---|---|---|---|
GPU Name | Ampere GA102-300 | Ampere GA102-200 | Ampere GA104-300 |
Process Node | Samsung 8N | Samsung 8N | Samsung 8N |
CUDA Cores | 10496 | 8704 | 5888 |
Boost Clock | 1700 MHz | 1710 MHz | 1730 MHz |
Memory Capacity | 24 GB GDDR6X | 10 GB GDDR6X | 8 GB GDDR6 |
Memory Bus | 384-bit | 320-bit | 256-bit |
Bandwidth | 936 Gb/s | 760 Gb/s | 512 Gb/s |
Memory Speed | 19.5 Gbps | 19 Gbps | 16 Gbps |
TDP | 350W | 320W | 220W |
Price | $1,499 | $699 | $499 |
Release date | September 24 | September 17 | October |
The RTX 3070 will be available for $499 this October, which is a little later than the RTX 3080 and RTX 3090—announced for September 17 and September 24 respectively.