NVIDIA GeForce RTX 3070 vs NVIDIA GeForce GTX 660 Ti

The NVIDIA GeForce RTX 3070 is a desktop graphics card that launched in Q4 2020 with a MSRP of $499. It is built on the Ampere GPU microarchitecture (codename GA104) and is manufactured on a 8 nm process.

Memory

The RTX 3070 has 8 GB of GDDR6 memory, with a 1,750 MHz memory clock and a 256 bit interface. This gives it a memory bandwidth of 448 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 RTX 3070 includes 5,888 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,500 MHz and can dynamically boost its clock speed up to 1,725 MHz. Complementing the processing units are 184 texture mapping units (TMUs) for efficient texture filtering and 96 render output units (ROPs) for pixel processing. Additionally, the GPU features 184 tensor cores optimized for AI-accelerated workloads and 46 RT cores dedicated to real-time ray tracing calculations.

Compatibility & Power Consumption

The RTX 3070 occupies 2 PCIe expansion slots. It supports HDMI 2.1, DisplayPort 1.4a display connections. NVIDIA recommends a power supply of at least 550 W to handle the GPU's thermal design power (TDP) of 220 W.

Benchmark Performance & Value

The RTX 3070 has the 33rd best 3DMark 11 Performance GPU score among the 543 benchmarked GPUs in our database. It achieves 41.11% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 43,005 score and $499 launch price (MSRP) gives it a performance per dollar of 86.18. This is the 30th best in value for the 3DMark 11 Performance GPU benchmark.