

NVIDIA GeForce RTX 2080 Ti Founders Edition wins 3 of 10 benchmarks, averaging 125.8% 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 2080 Ti Founders Edition leads by 181% (98.34 vs 35.01 tok/s); the closest fight is Stable Diffusion XL (77% apart); VRAM decides part of this one: NVIDIA GeForce RTX 2080 Ti Founders Edition runs 111 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 2080 Ti Founders Edition | NVIDIA T4 | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 148.46 | 67.71 | +119% |
| Llama 3.1 8B tok/s | 98.34 | 35.01 | +181% |
| Qwen2.5-Coder 14B tok/s | 0 | 19.76 | 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 | 4.18 | 2.36 | +77% |
| 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 |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | NVIDIA T4 | |
|---|---|---|
| VRAM | 11GB | 16GB |
| Architecture | Turing (TU102) | Turing |
| Memory bandwidth | 616 GB/s | 320 GB/s |
| Boost clock | 1,545 MHz | 1,590 MHz |
| TDP | 250 W | 70 W |
| Launch MSRP | $1,199 | $2,299 |
| Release | 2018-09-20 | 2018-09-13 |
NVIDIA GeForce RTX 2080 Ti Founders Edition full review · NVIDIA T4 full review · All AI & Machine Learning rankings