NVIDIA GeForce RTX 5060 Ti — Benchmarks & Specs

Bottom line: how fast is the NVIDIA GeForce RTX 5060 Ti?

SpecPicks median: 57.0 tokens/sec across 4 cited single-user runs of 7-9B dense models at 4-bit (Q4) under llama.cpp (range 51.4–93.5 tok/s), from llama.cpp GitHub, LocalScore.ai, InsiderLLM, Hardware Corner. At the $721.17 Amazon price of the cheapest linked listing (checked 2026-10-15 22:14 UTC; prices change), that is a SpecPicks Value Index of 79.0 tok/s per $1,000. At 1440p Max, the NVIDIA GeForce RTX 5060 Ti averages 70 fps in Dragon's Dogma 2, per Gamers Nexus. For local LLM inference it generates 45.1 tokens/sec running qwen2.5-coder:14b at q4_K_M under ollama, per GPU Battle. In 3DMark Fire Strike it scores 40,925 points, per KitGuru. 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 (20.9B parameters, MXFP4), generating 111.5 tokens/sec under llama.cpp, per llama.cpp GitHub.

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.