AMD Radeon RX 6900 XT

The RX 6900 XT's strongest measured trait is frames per watt at 0.34 fps/W, which puts it in the 57th percentile — that metric describes how much of its power budget turns into frames. Its weakest is ray tracing retention at 33% of raster (13th 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 6900 XT turns a 300W board power budget into 102.1 fps at 1440p, or 0.34 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 5700 XT 50th Anniversary (2019), at 53.1 fps and 225W. The RX 6900 XT is 92% faster and draws 75W more.

Every rendered pixel has to be fed from memory. At 1440p the RX 6900 XT has 1,360 B/px of memory bandwidth available per pixel it draws, against a median of 1,808 B/px — a tight ratio, which is why its frame rate falls off harder than its shader count suggests as resolution and texture quality climb. 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 RX 6900 XT carries 16GB against a median of 12GB across the 12 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.