

NVIDIA GeForce RTX 3080 Ti wins 3 of 11 benchmarks, averaging 81% faster.
Both cards were measured first-party on our bench, same suite, same test rig.
The gap is widest in Llama 3.1 8B, where NVIDIA GeForce RTX 3080 Ti leads by 87% (76.93 vs 144.11 tok/s); the closest fight is Qwen3 4B (75% apart); VRAM decides part of this one: NVIDIA GeForce RTX 3080 Ti runs 3 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3080 Ti | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 118.21 | 206.45 | -43% |
| Llama 3.1 8B tok/s | 76.93 | 144.11 | -47% |
| Qwen2.5-Coder 14B tok/s | 0 | 78.31 | n/a |
| Qwen3 32B tok/s | 0 | 0 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Z-Image Turbo images/min | 0 | 0 | n/a |
| 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 | 0 | 0 | n/a |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
| NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3080 Ti | |
|---|---|---|
| VRAM | 8GB | 12GB |
| Transistors | 17,400M | 28,300M |
| Die size | 392.5 mm² | 628.4 mm² |
| Transistor density | 44.3 M/mm² | 45 M/mm² |
| Architecture | Ampere (GA104) | Ampere (GA102) |
| Memory bandwidth | 448 GB/s | 912.4 GB/s |
| Boost clock | 1,665 MHz | 1,665 MHz |
| TDP | 200 W | 350 W |
| Launch MSRP | $399 | $1,199 |
| Release | 2020-12-02 | 2021-06-03 |
NVIDIA GeForce RTX 3060 Ti full review · NVIDIA GeForce RTX 3080 Ti full review · All AI & Machine Learning rankings