RTX 3080 Ti cloud pricing, August 2026
Live RTX 3080 Ti quotes (12 GB VRAM) across the providers we track, cheapest first. Marketplace prices are real asks from the Vast.ai order book; secure/on-demand tiers carry datacenter SLAs (what the tiers mean).
Quotes refreshed 2026-08-23What fits on a single RTX 3080 Ti
Models from our tracked open-weight set that fit in 12 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).
| Model | Params | Fits at | VRAM needed | Cheapest API $/1M out |
|---|---|---|---|---|
| Llama 3.1 8B | 8B | FP8 | 11 GB | compare → |
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| IBM Granite 4.1 8B | 8.8B | INT4 | 7 GB | compare → |
| Gemma 3 12B | 12B | INT4 | 9 GB | compare → |
| Phi-4 | 14.7B | INT4 | 11 GB | compare → |
FAQ
How much does it cost to rent a RTX 3080 Ti?
As of 2026-08-23, RTX 3080 Ti rentals start at $0.180/hr (community tier at RunPod). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.
What can you run on a RTX 3080 Ti?
With 12 GB of VRAM, a single RTX 3080 Ti fits models up to roughly 8B parameters at FP8 or 17B at INT4 quantization, including KV-cache headroom.
Cite or embed today's floor
Live badge for a README. It updates itself with every daily refresh:
[](https://llmhosting.ai/gpus/rtx-3080-ti)
Citation: RTX 3080 Ti rental floor $0.180/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.