RTX 3080 Ti
The RTX 3080 Ti is a cloud GPU with 12 GB of memory and 350 W TDP. It is currently available from 4 providers starting at $0.06/hr, with a market median of $0.13/hr across 33 offerings.
Best deal
Hardware specifications
- Architecture
- Ampere
- VRAM
- 12 GB
- Memory type
- GDDR6X
- Memory bandwidth
- 912 GB/s
- FP32
- 34 TFLOPS
- TDP
- 350 W
Same across all providers.
Market comparison
9-day price history
Offerings
| Provider | Cloud | Count | vCPU | RAM | Region | Per GPU hr | SPOT | Total/hr | |
|---|---|---|---|---|---|---|---|---|---|
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | 31 GB | VN | $0.06/hr | — | $0.06/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | United Kingdom, GB | $0.07/hr | $0.03/hr | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Ukraine, UA | $0.07/hr | $0.05/hr | $0.07/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Germany, DE | $0.08/hr | $0.07/hr | $0.08/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Alberta, CA | $0.10/hr | $0.09/hr | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Spain, ES | $0.10/hr | $0.07/hr | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Quebec, CA | $0.10/hr | — | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | India, IN | $0.10/hr | $0.05/hr | $0.10/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | North Carolina, US | $0.11/hr | $0.08/hr | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Virginia, US | $0.11/hr | — | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Ontario, CA | $0.11/hr | $0.07/hr | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Wyoming, US | $0.11/hr | — | $0.11/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Laos, LA | $0.12/hr | — | $0.12/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Oregon, US | $0.12/hr | $0.11/hr | $0.12/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | New Jersey, US | $0.12/hr | $0.09/hr | $0.12/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | British Columbia, CA | $0.12/hr | $0.09/hr | $0.12/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Texas, US | $0.13/hr | $0.05/hr | $0.13/hr | Launch ↗ |
AutoDL 0.0% 30dReferral link | — | ×1 | — | — | CN | $0.13/hr | — | $0.13/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Pennsylvania, US | $0.14/hr | $0.13/hr | $0.14/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | California, US | $0.14/hr | $0.09/hr | $0.14/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Portugal, PT | $0.14/hr | $0.09/hr | $0.14/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Hungary, HU | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | France, FR | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | South Carolina, US | $0.15/hr | — | $0.15/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Japan, JP | $0.17/hr | $0.11/hr | $0.17/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×1 | — | — | — | $0.18/hr | — | $0.18/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Taiwan, TW | $0.18/hr | $0.17/hr | $0.18/hr | Launch ↗ |
RunPodPromoted 0.0% 30dReferral link | Community | ×1 | — | — | — | $0.18/hr | — | $0.18/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Global | $0.18/hr | — | $0.18/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | Thailand, TH | $0.18/hr | $0.17/hr | $0.18/hr | Launch ↗ |
GPU Finder 0.0% 30d | — | ×1 | — | — | theta-community | $0.22/hr | — | $0.22/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×2 | — | — | — | $0.18/hr | — | $0.36/hr | Launch ↗ |
HardwareHQ 0.0% 30dReferral link | — | ×4 | — | — | — | $0.18/hr | — | $0.72/hr | Launch ↗ |
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | Barely fits on 8× |
Llama 3.1 70B Meta | 70B | Needs >8 GPUs | Barely fits on 8× | Barely fits on 5× |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | Needs >8 GPUs | Barely fits on 5× | Barely fits on 3× |
Qwen3 32B Alibaba | 32.8B | Barely fits on 8× | 5× · 14% spare | 3× · 6 GB free |
Qwen2.5 14B Alibaba | 14B | Barely fits on 3× | 2× · 4.7 GB free | Barely fits on 1× |
Llama 3.1 8B Meta | 8B | Barely fits on 2× | Barely fits on 1× | 1× · 5.3 GB free |
Mistral 7B Mistral AI | 7B | 2× · 5.8 GB free | 1× · 2 GB free | 1× · 6.1 GB free |
Qwen3 4B Alibaba | 4B | Barely fits on 1× | 1× · 5.6 GB free | 1× · 8.3 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 3080 Ti cost per hour?
The cheapest RTX 3080 Ti offering starts at $0.06/hr, and the market median is $0.13/hr.
Which cloud providers offer the RTX 3080 Ti?
We track RTX 3080 Ti offerings from HardwareHQ, GPU Finder, AutoDL, RunPod.
How much VRAM does the RTX 3080 Ti have?
The RTX 3080 Ti has 12 GB of VRAM.
What LLMs can run on the RTX 3080 Ti?
With 12 GB of VRAM, the RTX 3080 Ti can run 8 of our tracked models in 4-bit quantization, including gpt-oss-120b, Qwen3.6 35B-A3B, Qwen3 32B. 5 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple RTX 3080 Tis?
With 8× RTX 3080 Ti (96 GB total), the largest tracked model that fits in 16-bit is Mistral 7B (7B params), which needs 2× GPUs.
Where is the RTX 3080 Ti cheapest?
The cheapest RTX 3080 Ti offering in our catalog is HardwareHQ at $0.06/hr per GPU-hour (×1).