AMD Radeon HD 6870 vs NVIDIA GeForce GTX 970

The NVIDIA GeForce GTX 970 is an end-of-life desktop graphics card that released in Q3 2014 with a MSRP of $329. It is built on the Maxwell 2.0 GPU microarchitecture (codename GM204) and is manufactured on a 28 nm process.

Memory

The GTX 970 has 4 GB of GDDR5 memory, with a 1,753 MHz memory clock and a 256 bit interface. This gives it a memory bandwidth of 224.4 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 970 includes 1,664 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,050 MHz and can dynamically boost its clock speed up to 1,178 MHz. Complementing the processing units are 104 texture mapping units (TMUs) for efficient texture filtering and 56 render output units (ROPs) for pixel processing.

Compatibility & Power Consumption

The GTX 970 occupies 2 PCIe expansion slots. It supports DVI, HDMI 2.0, DisplayPort 1.2 display connections. NVIDIA recommends a power supply of at least 300 W to handle the GPU's thermal design power (TDP) of 148 W.

Benchmark Performance & Value

The GTX 970 has the 138th best 3DMark 11 Performance GPU score among the 543 benchmarked GPUs in our database. It achieves 15.33% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 16,033 score and $329 launch price (MSRP) gives it a performance per dollar of 48.73. This is the 66th best in value for the 3DMark 11 Performance GPU benchmark.