RTX 2080 Ti
The RTX 2080 Ti is a cloud GPU with 11 GB of memory and 250 W TDP. It is currently available from 3 providers starting at $0.05/hr, with a market median of $0.08/hr across 19 offerings.
Best deal
Hardware specifications
- Architecture
- Turing
- VRAM
- 11 GB
- Memory bandwidth
- 616 GB/s
- FP32
- 13 TFLOPS
- TDP
- 250 W
Same across all providers.
Market comparison
All-time price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
GPU Finder 0.0% 30d | — | ×1 | — | — | Michigan, US | $0.05/hr | $0.03/hr | $0.05/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Yunnan, CN | $0.06/hr | $0.05/hr | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Malaysia, MY | $0.06/hr | $0.05/hr | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Vietnam, VN | $0.06/hr | $0.05/hr | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | India, IN | $0.07/hr | $0.04/hr | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Quebec, CA | $0.07/hr | — | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | California, US, Hong Kong, HK, Shanghai, CN | $0.07/hr | — | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | British Columbia, CA | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Florida, US | $0.08/hr | $0.05/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | United States, US | $0.08/hr | $0.07/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Nevada, US | $0.08/hr | $0.07/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Thailand, TH | $0.09/hr | $0.07/hr | $0.09/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Henan, CN | $0.09/hr | — | $0.09/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Brazil, BR | $0.09/hr | $0.04/hr | $0.09/hr | Launch ↗ |
AI Galaxy 0.0% 30dReferral link | — | ×1 | — | — | CN | $0.11/hr | — | $0.11/hr | Launch ↗ |
AutoDL 0.0% 30dReferral link | — | ×1 | — | — | CN | $0.12/hr | — | $0.12/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Maryland, US | $0.13/hr | $0.11/hr | $0.13/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | New Jersey, US | $0.13/hr | $0.12/hr | $0.13/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Washington, US | $0.67/hr | $0.40/hr | $0.67/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Needs >8 GPUs | Barely fits on 5× |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | Needs >8 GPUs | 6× · 14.5% spare | 4× · 10.4 GB free |
Qwen3 32B Alibaba | 32.8B | Needs >8 GPUs | Barely fits on 5× | Barely fits on 3× |
Qwen2.5 14B Alibaba | 14B | 4× · 8.6 GB free | Barely fits on 2× | 2× · 10.6 GB free |
Llama 3.1 8B Meta | 8B | Barely fits on 2× | 2× · 10.6 GB free | 1× · 4.3 GB free |
Mistral 7B Mistral AI | 7B | 2× · 3.8 GB free | Barely fits on 1× | 1× · 5.1 GB free |
Qwen3 4B Alibaba | 4B | 2× · 10.4 GB free | 1× · 4.6 GB free | 1× · 7.3 GB free |
Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.
Similar GPUs
See more GPUs like this in
Frequently asked questions
How much does the RTX 2080 Ti cost per hour?
The cheapest RTX 2080 Ti offering starts at $0.05/hr, and the market median is $0.08/hr.
Which cloud providers offer the RTX 2080 Ti?
We track RTX 2080 Ti offerings from GPU Finder, AI Galaxy, AutoDL.
How much VRAM does the RTX 2080 Ti have?
The RTX 2080 Ti has 11 GB of VRAM.
What LLMs can run on the RTX 2080 Ti?
With 11 GB of VRAM, the RTX 2080 Ti can run 7 of our tracked models in 4-bit quantization, including Qwen3.6 35B-A3B, Qwen3 32B, Llama 3.1 70B. 4 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple RTX 2080 Tis?
With 8× RTX 2080 Ti (88 GB total), the largest tracked model that fits in 16-bit is Qwen2.5 14B (14B params), which needs 4× GPUs.
Where is the RTX 2080 Ti cheapest?
The cheapest RTX 2080 Ti offering in our catalog is GPU Finder at $0.05/hr per GPU-hour (×1).