11GB · AI Score 2.2/100 · first-party measured on 12 AI workloads
2.2 AI Score Includes estimates
Every number on this page is first-party: NVIDIA GeForce RTX 2080 Ti Founders Edition was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) NVIDIA GeForce RTX 2080 Ti Founders Edition delivers about 98.34 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 11GB. For image generation, SDXL runs at 2.09 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 9 of the 12 workloads won't fit on 11GB at the tested precision, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo and others. We publish those as hard gates rather than quietly dropping to a smaller quant.
Oldest card in my top tier and it still hangs on for small LLMs, but it works hard for it: 104% of its 250W rating on SDXL, and the worst efficiency I measured in this class at 0.79 tokens/watt. The 11GB keeps 8 of 12 workloads out. One flagged gate pending re-run. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 148.46 tok/s | 2.6 GB peak187 W42°C0.79 tok/WQ4_K_M | ✓ Measured |
| Llama 3.1 8B | 98.34 tok/s | 4.8 GB peak211 W48°C0.47 tok/WQ4_K_M | ✓ Measured |
| Qwen2.5-Coder 14B | ✕ Won't fit needs ~12 GB | VRAM-gated at this precision | ✓ Measured |
| Gemma 4 26B A4B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Qwen3 30B A3B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Gemma 4 31B | ✕ Won't fit needs ~22 GB | VRAM-gated at this precision | Est. |
| Qwen3 32B | ✕ Won't fit needs ~23 GB | VRAM-gated at this precision | ✓ Measured |
| Llama 3.3 70B | ✕ Won't fit needs ~46 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 4.18 images/min | 6 GB peak217 W71°C14.4 s/img | ✓ Measured CPU offload |
| Z-Image Turbo | ✕ Won't fit needs ~13 GB | VRAM-gated at this precision | ✓ Measured |
| PixArt-Sigma XL | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | Est. |
| FLUX.1 dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen-Image-Edit | ✕ Won't fit needs ~42 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | ✓ Measured |
| Wan 2.2 5B (720p) | ✕ Won't fit needs ~18 GB | VRAM-gated at this precision | ✓ Measured |
| Architecture | Turing (TU102) |
| CUDA cores | 4,352 |
| VRAM | 11GB GDDR6 |
| Memory bus | 352-bit |
| Memory bandwidth | 616 GB/s |
| Boost clock | 1,545 MHz |
| TDP | 250 W |
| Process | 12nm |
| Interface | PCIe 3.0 x16 |
| Release date | 2018-09-20 |
| Launch MSRP | $1,199 |
NVIDIA GeForce RTX 2080 Ti Founders Edition scores 2.2/100, #77 of 102. It ran 3 of 12; 9 exceeded its 11GB. Every figure here is our own measurement.
100% = this card, AI & Machine Learning headline metric (AI Score). #38 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| GeForce GTX 1080 Ti | 105% | 2.3 | |
| NVIDIA GeForce RTX 3080 | 105% | 2.3 | |
| NVIDIA TITAN Xp | 105% | 2.3 | |
| AMD Radeon RX 7700 XT | 100% | 2.2 | |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | 100% | 2.2 | |
| NVIDIA GeForce RTX 3070 Ti | 100% | 2.2 | |
| NVIDIA GeForce RTX 2080 Super | 95% | 2.1 | |
| NVIDIA GeForce RTX 3070 Founders Edition | 95% | 2.1 | |
| NVIDIA GeForce RTX 5060 | 95% | 2.1 |
Same card, other workloads: NVIDIA GeForce RTX 2080 Ti Founders Edition Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 18,600 million |
| Die size | 754 mm² |
| Process node | 12 nm |
| Fabricated by | TSMC |
| Transistor density | 24.7 million per mm² |
Denser than 69% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
Can't run: Product photo shoot (needs FLUX.1 Kontext dev), Photo restoration batch (needs FLUX.1 Kontext dev), Restore and enlarge photos (needs FLUX.1 Kontext dev), Character sheet, 12 poses (needs FLUX.1 dev), Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B).
This card is $1,199 to buy. The cheapest listed rate on Vast.ai is $0.101/hour, but that is the floor: we budget $0.121/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 9,893 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $88 | 13.6 years |
| 8 hours a day, working on it | 2,920 | $354 | 3.4 years |
| 24/7, always-on agent | 8,760 | $1,062 | 1.1 years |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.