GeForce RTX 2080 Ti
NVIDIA
11GB VRAM · 616 GB/s bandwidth · 26.9 FP16 TFLOPS · 250W TDP
The GeForce RTX 2080 Ti has 11GB of VRAM with 616 GB/s memory bandwidth and 26.9 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (178 tok/s), Qwen 2.5 7B (94 tok/s), Llama 3.1 8B (88 tok/s). Models larger than ~19B parameters won't fit even at Q4. Electricity cost is approximately $27/month at 250W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 178 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 94 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 88 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | won't fit | |
| Gemma 3 27B | 27.4B | 14 GB | won't fit | |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | won't fit | |
| Llama 3.3 70B | 70.6B | 35 GB | won't fit | |
| Qwen 2.5 72B | 72.7B | 36 GB | won't fit | |
| Llama 3.1 405B | 405B | 202 GB | won't fit | |
| DeepSeek R1 671B | 671B | 336 GB | won't fit |
Similar GPUs
| GPU | VRAM | BW | TFLOPS | TDP |
|---|---|---|---|---|
| GeForce GTX 1080 Ti | 11GB | 484 GB/s | 0.2 | 250W |
| TITAN V | 12GB | 651 GB/s | 29.8 | 250W |
| GeForce RTX 5070 | 12GB | 672 GB/s | 30.9 | 250W |
| Tesla P100 PCIe 12 GB | 12GB | 549 GB/s | 19.1 | 250W |
| TITAN Xp | 12GB | 547 GB/s | 0.2 | 250W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.