NVIDIA GeForce GTX 1080 Ti

The GTX 1080 Ti's strongest measured trait is bandwidth per pixel at 2,615 B/px, which puts it in the 94th percentile — that metric describes memory bandwidth available for every pixel it draws at 1440p. Its weakest is frames per $100 at 7.2 fps/$100 (4th 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 1080 Ti turns a 250W board power budget into 50.2 fps at 1440p, or 0.20 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.

Every rendered pixel has to be fed from memory. At 1440p the GTX 1080 Ti has 2,615 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.

The GTX 1080 Ti ranks #49 in 3DMark Steel Nomad but #58 on the 1440p game average — 9 places lower in real games than the synthetic implies. Steel Nomad is a 4K, non-ray-traced pass with heavy async compute and no upscaling, so it rewards raw shader and bandwidth throughput and ignores driver overhead, geometry front-end limits, and everything a game engine does outside the compute path. A gap this size means the hardware on paper is ahead of what the driver and engine mix currently extract from it.

On memory capacity, the GTX 1080 Ti carries 11GB against a median of 8GB across the 9 other cards within 10% of its 1440p frame rate. It carries more memory than its performance class typically ships with, which mostly matters for high-resolution textures, local AI models, and viewport-heavy creative work rather than frame rate.

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.