AMD Radeon R9 390X vs NVIDIA GeForce GTX 1070

The NVIDIA GeForce GTX 1070 is an end-of-life desktop graphics card that released in Q2 2016 with a MSRP of $379. It is built on the Pascal GPU microarchitecture (codename GP104) and is manufactured on a 16 nm process.

Memory

The GTX 1070 has 8 GB of GDDR5 memory, with a 2,002 MHz memory clock and a 256 bit interface. This gives it a memory bandwidth of 256.3 Gb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.

Cores and Clock Speeds

The GTX 1070 includes 1,920 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,506 MHz and can dynamically boost its clock speed up to 1,683 MHz. Complementing the processing units are 120 texture mapping units (TMUs) for efficient texture filtering and 64 render output units (ROPs) for pixel processing.

Compatibility & Power Consumption

The GTX 1070 occupies 2 PCIe expansion slots. It supports DVI, HDMI 2.0, DisplayPort 1.4a display connections. NVIDIA recommends a power supply of at least 450 W to handle the GPU's thermal design power (TDP) of 150 W.

Benchmark Performance & Value

The GTX 1070 has the 95th best 3DMark 11 Performance GPU score among the 543 benchmarked GPUs in our database. It achieves 23.54% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 24,652 score and $379 launch price (MSRP) gives it a performance per dollar of 65.04. This is the 50th best in value for the 3DMark 11 Performance GPU benchmark.