AMD Radeon RX 7800 XT — Benchmarks & Specs

Bottom line: how fast is the Radeon RX 7800 XT?

SpecPicks median: 81.7 tokens/sec across 6 cited single-user runs of 7-9B dense models at 4-bit (Q4) under llama.cpp (range 34.1–125 tok/s), from llama.cpp GitHub Discussions (4 runs), LocalScore.ai (2 runs). At the $978.00 Amazon price of the cheapest linked listing (checked 2026-10-13 16:14 UTC; prices change), that is 83.6 tok/s per $1,000. At 1440p Ultra, the Radeon RX 7800 XT averages 116 fps in Total War: Warhammer III, per Gamers Nexus. For local LLM inference it generates 23.0 tokens/sec running qwen2.5:14b at q4_K_M under llama.cpp, per LocalScore.ai. In 3DMark Fire Strike it scores 27,435 points, per Overclocking.com. It has 16 GB of VRAM, and the qwen2.5:14b run above (14B parameters) is the largest model on file at 4-bit quantization on this card. Larger models have no sourced run on file.

Every figure above is a row in the tables below, and each row links out to the review or public benchmark database the number was taken from; the SpecPicks median is computed here from the runs it names, each a row in the AI table, and the per-$1,000 figure divides it by the dated listing price. SpecPicks aggregates published measurements; it does not report first-party benchmark runs.