AMD Radeon RX 6500 XT

The RX 6500 XT's strongest measured trait is bandwidth per pixel at 2,170 B/px, which puts it in the 69th percentile — that metric describes memory bandwidth available for every pixel it draws at 1440p. Its weakest is frames per watt at 0.17 fps/W (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 RX 6500 XT turns a 107W board power budget into 18 fps at 1440p, or 0.17 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 AMD card from an earlier generation is the AMD Radeon RX 570 (2017), at 19.9 fps and 120W. The RX 6500 XT is 10% slower while drawing 13W less.

Every rendered pixel has to be fed from memory. At 1440p the RX 6500 XT has 2,170 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.

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.