RTX 4090 vs RTX 3090

Across 9 matched pairs (same model, size and quant, same runtime family, chat-short), the RTX 4090 decoded 0.8% to 22.5% faster than the RTX 3090, with a median of 14.9%: the smallest lead was Llama 3.1 8B on Ollama (137.32 vs 136.20 tok/s, r_2np7abzjobe vs r_9hurqggbshk) and the largest was GLM-4.7-Flash on Ollama (164.94 vs 134.62 tok/s, r_ted0u8uyre0 vs r_kalwcyab-86). Leads are calculated from single measured runs on different hosts, and the llama.cpp pairs used different llama.cpp builds. On Qwen3.8-27B the gap was about 14% on all four workloads (r_11kn1epxewh vs r_ptct8o01o5l). Three overlaps are listed separately as not like-for-like: gemma3 (4.3B vs 11.8B), the Nemotron Bolt runs (no quant reported) and qwen2.5-coder 7.6B (the RTX 3090 request included a cold model load). Both are 24GB cards. They ran on different hosts and llama.cpp builds, so these are measured reference points, not a controlled ranking. Older Ollama runs from a host whose RTX 4090 reports 48GB of GPU memory are excluded here: a retail RTX 4090 has 24GB, and we can't confirm what that card is. For whether the upgrade is worth buying, read our RTX 3090 vs 4090 buying explanation.