NVIDIA GeForce RTX 4070 Ti — Benchmarks & Specs

Bottom line: how fast is the GeForce RTX 4070 Ti?

SpecPicks median: 78.0 tokens/sec across 9 cited single-user runs of 7-9B dense models at 4-bit (Q4) under llama.cpp (range 42.1–97.0 tok/s), from Markaicode, GPU-Benchmarks-on-LLM-Inference (4 runs), Kunal Ganglani LLM Benchmarks, Hardware Corner (3 runs). At the $1,149.00 Amazon price of the cheapest linked listing (checked 2026-10-20 22:16 UTC; prices change), that is a SpecPicks Value Index of 67.9 tok/s per $1,000. One of those runs: llama3.1:8b at q4_K_M generates 97.0 tokens/sec under llama.cpp, per Markaicode. At 1440p Ultra, the GeForce RTX 4070 Ti averages 127 fps in Far Cry 6, per Beebom. In PassMark G3D Mark it scores 31,573 pts, per PassMark. Its 12 GB of VRAM is the binding constraint for local inference: the largest model on file at 4-bit quantization on this card is deepseek-r1:14b (14B parameters, q4_K_M), generating 49.7 tokens/sec under llama.cpp, per geerlingguy/ai-benchmarks.

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.