11GB · AI Score 1.9/100 · anchored estimate vs 51 measured cards
2.3 AI Score Includes estimates
We have not run GeForce GTX 1080 Ti on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: moderate). On Llama 3.1 8B (Q4_K_M) GeForce GTX 1080 Ti should deliver about 56.2 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 11GB. For image generation, SDXL should run near 0.84 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.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3-4B | 78.25 tok/s | 222 W65°CQ4_K_M | ✓ Measured |
| Llama-3.1-8B | 50.52 tok/s | 234 W67°CQ4_K_M | ✓ Measured |
| Qwen3 8B | 49.08 tok/s | 241 W68°CQ4_K_M | ✓ Measured |
| Gemma 4 12B | 31.19 tok/s | 233 W70°CQ4_K_M | ✓ Measured |
| Qwen2.5-Coder-14B | 27.36 tok/s | 255 W72°CQ4_K_M | ✓ Measured |
| Qwen3 14B | 27.84 tok/s | 248 W71°CQ4_K_M | ✓ 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 | VRAM-gated at this precision | Est. |
| Llama 3.3 70B | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 1.68 images/min | estimated | Est. |
| PixArt-Sigma XL | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | Est. |
| FLUX.1 dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Z-Image Turbo | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Qwen-Image-Edit | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Wan 2.2 5B (720p) | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Architecture | Pascal (GP102) |
| CUDA cores | 3,584 |
| VRAM | 11GB GDDR5X |
| Memory bus | 352-bit |
| Memory bandwidth | 484 GB/s |
| Boost clock | 1,582 MHz |
| TDP | 250 W |
| Process | 16nm |
| Interface | PCIe 3.0 x16 |
| Release date | 2017-03-10 |
| Launch MSRP | $699 |
GeForce GTX 1080 Ti scores 1.9/100, #73 of 102. It ran 3 of 12; 9 exceeded its 11GB. Figures are anchored estimates, not measurements, we flag that on every row.
100% = this card, AI & Machine Learning headline metric (AI Score). #34 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| AMD Radeon RX 6800 XT | 100% | 2.3 | |
| AMD Radeon RX 6800 | 100% | 2.3 | |
| AMD Radeon RX 6900 XT | 100% | 2.3 | |
| AMD Radeon RX 6950 XT | 100% | 2.3 | |
| GeForce GTX 1080 Ti | 100% | 2.3 | |
| NVIDIA GeForce RTX 3080 | 100% | 2.3 | |
| NVIDIA TITAN Xp | 100% | 2.3 | |
| AMD Radeon RX 7700 XT | 96% | 2.2 | |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | 96% | 2.2 |
Same card, other workloads: GeForce GTX 1080 Ti Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 12,000 million |
| Die size | 471 mm² |
| Process node | 16 nm |
| Fabricated by | TSMC |
| Transistor density | 25.5 million per mm² |
Denser than 73% 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.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| Full codebase review | 36.6 min | 155.09 Wh | measured |
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).
This card is $699 to buy. The cheapest listed rate on Vast.ai is $0.065/hour, but that is the floor: we budget $0.078/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 8,962 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 | $57 | 12.3 years |
| 8 hours a day, working on it | 2,920 | $228 | 3.1 years |
| 24/7, always-on agent | 8,760 | $683 | 1.0 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.