NVIDIA GeForce RTX 4070 SUPER — Benchmarks & Specs

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

SpecPicks median: 75.0 tokens/sec across 7 cited single-user runs of 7-9B dense models at 4-bit (Q4) under llama.cpp (range 45.3–109 tok/s), from llama.cpp GitHub Discussions, MyAIHardware, Hardware Corner (2 runs), Mustafa.net LLM Benchmark, LocalScore (2 runs). At the $959.00 Amazon price of the cheapest linked listing (checked 2026-10-14 10:15 UTC; prices change), that is 78.2 tok/s per $1,000. At 1440p High, the GeForce RTX 4070 SUPER averages 111 fps in Dying Light 2: Stay Human, per Gamers Nexus. For local LLM inference it generates 40.0 tokens/sec running Generic 13B LLM at q4_K_M under llama.cpp, per Mustafa.net LLM Benchmark. In 3DMark Fire Strike it scores 40,528 points, per Overclocking.com. 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 Qwen2.5 14B Instruct (14.8B parameters, q4_K_M), generating 24.9 tokens/sec under llama.cpp, per LocalScore.

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.