

NVIDIA GeForce RTX 3090 Ti wins 6 of 12 benchmarks, averaging 19.7% faster.
Both cards were measured first-party on our bench, same suite, same test rig.
The gap is widest in Z-Image Turbo, where NVIDIA GeForce RTX 3090 Ti leads by 71% (4.35 vs 2.55 images/min); the closest fight is LTX-Video (distilled) (1% apart); VRAM decides part of this one: NVIDIA GeForce RTX 3090 Ti runs 8 of our 12 AI workloads while the other card runs 6, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 4080 | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 227.54 | 201.76 | +13% |
| Llama 3.1 8B tok/s | 161.02 | 127.09 | +27% |
| Qwen2.5-Coder 14B tok/s | 88.25 | 69.93 | +26% |
| Qwen3 32B tok/s | 42.18 | 0 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Stable Diffusion XL images/min | 8.42 | 10.16 | -17% |
| Z-Image Turbo images/min | 4.35 | 2.55 | +71% |
| FLUX.1 dev images/min | 0 | 0 | n/a |
| FLUX.1 Kontext dev images/min | 0 | 0 | n/a |
| Qwen-Image-Edit images/min | 0 | 0 | n/a |
| LTX-Video (distilled) frames/s | 3.2 | 3.23 | -1% |
| Wan 2.2 5B (720p) frames/s | 0.27 | 0 | n/a |
How long each card takes to finish a complete pipeline, not just one model. NVIDIA GeForce RTX 3090 Ti is faster on 1 of 1; NVIDIA GeForce RTX 4080 on 0.
| Workflow | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 4080 | Difference | Cost per run |
|---|---|---|---|---|
| Full codebase review | 11.3 min | 14.3 min | NVIDIA GeForce RTX 3090 Ti 1.26x faster | $0.051 vs $0.026 |
Renting by the hour, NVIDIA GeForce RTX 4080 finishes 1 of 1 cheaper. The quicker card is not automatically the cheaper way to get the work done.
| Card | Per hour |
|---|---|
| NVIDIA GeForce RTX 3090 Ti | $0.270 |
| NVIDIA GeForce RTX 4080 | $0.108 |
NVIDIA GeForce RTX 4080 is 2.50x cheaper per hour. Cheapest on-demand rate we see across RunPod and Vast.
| NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 4080 | |
|---|---|---|
| VRAM | 24GB | 16GB |
| Transistors | 28,300M | 45,900M |
| Die size | 628.4 mm² | 378.6 mm² |
| Transistor density | 45 M/mm² | 121.2 M/mm² |
| Architecture | Ampere (GA102) | Ada Lovelace (AD103) |
| Memory bandwidth | 1008 GB/s | 716.8 GB/s |
| Boost clock | 1,860 MHz | 2,505 MHz |
| TDP | 450 W | 320 W |
| Launch MSRP | $1,999 | $1,199 |
| Release | 2022-03-29 | 2022-11-16 |
NVIDIA GeForce RTX 3090 Ti full review · NVIDIA GeForce RTX 4080 full review · All AI & Machine Learning rankings