NVIDIA GeForce GTX 1660 Super

The GTX 1660 Super's strongest measured trait is bandwidth per pixel at 2,737 B/px, which puts it in the 96th percentile — that metric describes memory bandwidth available for every pixel it draws at 1440p. Its weakest is frames per watt at 0.27 fps/W (26th percentile). That is a wide spread for a single card: it is specialised rather than balanced, and whether it suits you depends on which of the two you actually load.

The GTX 1660 Super turns a 125W board power budget into 33.3 fps at 1440p, or 0.27 fps/W against a pool median of 0.32 fps/W. Power, not transistor count, is the binding constraint on a modern GPU — Dennard scaling stopped holding around 2005, and Esmaeilzadeh and colleagues showed at ISCA 2011 that the fraction of a chip that can be powered at full speed shrinks with every node (“dark silicon”). Frames per watt is the shortest honest summary of what an architecture is doing with that budget.

For scale: the closest NVIDIA card from an earlier generation is the NVIDIA GeForce GTX 1070 (2016), at 33.1 fps and 150W. The GTX 1660 Super is the same speed while drawing 25W less.

Every rendered pixel has to be fed from memory. At 1440p the GTX 1660 Super has 2,737 B/px of memory bandwidth available per pixel it draws, against a median of 1,808 B/px — comfortably fed, so its shaders are the limit before its memory is. This is the roofline model applied to a game frame: Williams, Waterman and Patterson (Communications of the ACM, 2009) showed that any workload runs into either a compute ceiling or a memory-bandwidth ceiling, and that the ratio of the two is what decides which one you hit.

On memory capacity, the GTX 1660 Super carries 6GB against a median of 6GB across the 3 other cards within 10% of its 1440p frame rate. That matches its class, so capacity is unlikely to be the first thing that limits it.

Method: percentiles are computed over the 77 non-legacy cards with a 1440p figure. Frame rates come from Tom's Hardware GPU hierarchy; specifications from manufacturer datasheets. Theoretical FP32 TFLOPS is deliberately not used as a cross-vendor comparison — RDNA 3 and 4 dual-issue FP32 doubles the paper figure without doubling game performance, and AMD itself declined to count it as extra shaders. The measured Steel Nomad score is used as the compute proxy instead. GPURanker does not run its own benchmarks.