RTX 3090 Ti vs RTX 4090 for local AI
Both fit the same models we track, up to Qwen3 32B. They generate at about the same speed, since their memory bandwidth is close (1008 and 1008 GB/s).
Memory and bandwidth
Memory decides which models fit. Bandwidth decides how fast they generate, because every token reads the model's active weights once.
| RTX 3090 Ti | RTX 4090 | |
|---|---|---|
| Memory | 24 GB VRAM | 24 GB VRAM |
| Bandwidth | 1008 GB/s | 1008 GB/s |
| Biggest model that fits | Qwen3 32B | Qwen3 32B |
| Best everyday pick | Qwen3 32B, ~28 tok/s | Qwen3 32B, ~28 tok/s |
Every model, side by side
Estimated generation speed at the largest memory size each was sold in (24 GB and 24 GB).
| Model | RTX 3090 Ti | RTX 4090 |
|---|---|---|
| Qwen3 4B About 4 GB | ~220 tok/s Runs great | ~220 tok/s Runs great |
| Qwen3 8B About 7 GB | ~110 tok/s Runs great | ~110 tok/s Runs great |
| Gemma 3 12B About 10 GB | ~68 tok/s Runs great | ~68 tok/s Runs great |
| Qwen3 14B About 11 GB | ~60 tok/s Runs great | ~60 tok/s Runs great |
| gpt-oss 20B About 16 GB | ~180 tok/s Runs great | ~180 tok/s Runs great |
| Gemma 3 27B About 19 GB | ~33 tok/s Runs great | ~33 tok/s Runs great |
| Qwen3 30B-A3B About 21 GB | ~180 tok/s Runs great | ~180 tok/s Runs great |
| Qwen3 32B About 22 GB | ~28 tok/s Usable | ~28 tok/s Usable |
| Llama 3.3 70B About 45 GB | Needs 45 GB | Needs 45 GB |
| gpt-oss 120B About 67 GB | Needs 67 GB | Needs 67 GB |
| Qwen3 235B-A22B About 144 GB | Needs 144 GB | Needs 144 GB |
| DeepSeek R1 671B About 406 GB | Needs 406 GB | Needs 406 GB |
They're close for local AI, so pick on price. Price matters as much as either number: check used prices on the builds page, where every parts list has a measured or estimated speed.
Both columns use the same formula: memory bandwidth divided by the weights read per token, calibrated on our own rack, with Ollama's default 4-bit sizes. Real results are usually within about a third. Measured either one? Send us the number.