AMD Radeon RX 9070 XT — Benchmarks & Specs

Bottom line: how fast is the Radeon RX 9070 XT?

SpecPicks median: 109 tokens/sec across 6 cited single-user runs of 7-9B dense models at 4-bit (Q4) under llama.cpp (range 92.3–143 tok/s), from llama.cpp GitHub (3 runs), RunAIHome, Vache Sarkissian, Local AI Master. At the $879.99 Amazon price of the cheapest linked listing (checked 2026-10-22 10:15 UTC; prices change), that is a SpecPicks Value Index of 123.7 tok/s per $1,000. At 1440p Ultra, the Radeon RX 9070 XT averages 118 fps in Final Fantasy XIV: Dawntrail, per Gamers Nexus. For local LLM inference it generates 52.2 tokens/sec running qwen3:14b at q4_K_M under ollama, per GitHub hirokuze/local-llm-benchmark-rx9070xt. In 3DMark Fire Strike it scores 66,762–67,571 points, across two LANOC results (LANOC result of 2025-05-30, LANOC result of 2025-03-21). Its 16 GB of VRAM is the binding constraint for local inference: the largest model on file at 4-bit quantization on this card is gpt-oss:20b (20B parameters, Q4_K_M), generating 91.9 tokens/sec under ollama, per GitHub hirokuze/local-llm-benchmark-rx9070xt.

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.