

NVIDIA GeForce RTX 3070 Ti wins 3 of 12 benchmarks, averaging 24.1% 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 3070 Ti leads by 26% (80.95 vs 102.13 tok/s); the closest fight is Qwen3 4B (22% apart).
| Benchmark | NVIDIA GeForce RTX 3070 Founders Edition | NVIDIA GeForce RTX 3070 Ti | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 126.36 | 154.65 | -18% |
| Llama 3.1 8B tok/s | 80.95 | 102.13 | -21% |
| Qwen2.5-Coder 14B tok/s | 0 | 0 | n/a |
| Qwen3 32B tok/s | 0 | 0 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Stable Diffusion XL images/min | 3.04 | 3.76 | -19% |
| 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 3070 Founders Edition | NVIDIA GeForce RTX 3070 Ti | |
|---|---|---|
| VRAM | 8GB | 8GB |
| Transistors | 17,400M | 17,400M |
| Die size | 392.5 mm² | 392.5 mm² |
| Transistor density | 44.3 M/mm² | 44.3 M/mm² |
| Architecture | Ampere | Ampere (GA104) |
| Memory bandwidth | 448 GB/s | 608 GB/s |
| Boost clock | 1,725 MHz | 1,770 MHz |
| TDP | 220 W | 290 W |
| Launch MSRP | $499 | $599 |
| Release | 2020-10-29 | 2021-06-10 |
NVIDIA GeForce RTX 3070 Founders Edition full review · NVIDIA GeForce RTX 3070 Ti full review · All AI & Machine Learning rankings