First-gen RTX with Tensor Cores and NVLink at low cost.
Weekly median price per GPU per hour · Get the data
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One RTX 2080 Ti has 11 GB of VRAM. Even at 4-bit, the weights of most modern AI models exceed the card's usable VRAM, and context adds KV cache on top. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | RTX 2080 Tis needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
3
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
7
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
19
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
25
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
31
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
157
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia RTX 2080 Ti · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 53.8 TFLOPS |
| INT8 | 215.2 TOPS |
| FP32 | 13.4 TFLOPS |
| Precision support | FP16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 11 GB GDDR6 |
| Bandwidth | 616 GB/s |
| Bus width | 352-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Turing |
| Process | TSMC 12 nm FFN |
| Transistors | 18.6 billion |
| Shader cores | 4,352 CUDA cores |
| Matrix cores | 544 Tensor cores |
| Compute units | 68 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 100 GB/s |
| Host interface | PCIe 3.0 x16 |
| Power | |
|---|---|
| Board power | 250 W |
| Cooling | Active |
The cheapest verified in-stock estimate is $58 per month on-demand, $29 spot.
GetDeploying currently tracks RTX 2080 Ti configs from 2 providers. Vast.ai has verified in-stock on-demand configs. See the full price comparison above for every provider and config.
More than one: even at 4-bit, the weights of most modern AI models exceed one RTX 2080 Ti's usable VRAM, and context adds KV cache on top. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
11GB GDDR6 with NVLink (100 GB/s). First-gen RTX with Tensor Cores. Very low cost on the secondary market.
Turing lacks BF16 and FP8. 11GB VRAM is limiting. Subject to Nvidia's consumer EULA, which may restrict data center use. Better options available at similar cloud pricing.
Nvidia RTX 3080 Ti
12 GB GDDR6X · 48% more bandwidth than the RTX 2080 Ti
Nvidia RTX 4070 Ti
12 GB GDDR6X · 18% less bandwidth than the RTX 2080 Ti
Nvidia RTX 2080
8 GB GDDR6 · 27% less bandwidth than the RTX 2080 Ti
Last updated
