AI GPU Benchmark Results
Every benchmark number in our database, with its source and evidence type. Filter by workload or evidence type; sort by any column. Independent benchmarks come from third-party reviews and standardized databases (MLPerf); community results are labeled reproducible when the run config is published, estimated when approximated.
Filter results
100 benchmark results
| GPU | Workload | Model / config | Result | Evidence | Source |
|---|---|---|---|---|---|
| GeForce RTX 4090 | Image generation | FLUX.1-dev · BF16 · Diffusers (Requires memory-efficient attention (xFormers/SDPA) within 24GB; approximate) | 4 img/min EST | Estimated0.40 | Spheron GPU Benchmark Blog |
| GeForce RTX 4090 | Image generation | SDXL Turbo · FP16 · ComfyUI | 80 img/min | Independent benchmark0.85 | Tom's Hardware GPU Benchmarks 2025 |
| GeForce RTX 4090 | Image generation | Stable Diffusion 1.5 · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 1.188 s/image) | 5,260 score | Independent benchmark0.85 | StorageReview GPU Reviews |
| GeForce RTX 4090 | Image generation | Stable Diffusion 1.5 INT8 · INT8 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.503 s/image) | 62,160 score | Independent benchmark0.85 | StorageReview GPU Reviews |
| GeForce RTX 4090 | Image generation | Stable Diffusion XL · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 7.461 s/image) | 5,025 score | Independent benchmark0.85 | StorageReview GPU Reviews |
How these numbers are sourced
Every row links to its original source and carries an evidence type plus a confidence score. Independent benchmarks come from third-party reviews (Tom's Hardware, TechPowerUp, Puget Systems) and standardized databases (MLPerf); manufacturer benchmarks are vendor-published figures; community results are reproducible when the run config is published, unverified otherwise — always labeled EST when estimated. Read the full benchmark methodology.
Compare any two GPUs head-to-head in the comparison tool, or browse value rankings.