Budget Turing GPU for basic local compute tasks.
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 2070 has 8 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 2070s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
3
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
4
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
10
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
25
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
34
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
43
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
215
|
–
|
–
|
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 2070 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 29.9 TFLOPS |
| INT8 | 119.4 TOPS |
| FP32 | 7.5 TFLOPS |
| Precision support | FP16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 8 GB GDDR6 |
| Bandwidth | 448 GB/s |
| Bus width | 256-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Turing |
| Process | TSMC 12 nm FFN |
| Transistors | 10.8 billion |
| Shader cores | 2,304 CUDA cores |
| Matrix cores | 288 Tensor cores |
| Compute units | 36 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 3.0 x16 |
| Power | |
|---|---|
| Board power | 175 W |
| Cooling | Active |
Source: official Nvidia RTX 2070 datasheet.
As of October 3, 2026, the median on-demand price is $0.06 per GPU per hour across 3 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 5 | $0.06 | $0.06 (in stock, Salad) |
Spot | 4 | $0.02 |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type.
The cheapest verified in-stock on-demand RTX 2070 tracked by GetDeploying is $0.06 per GPU per hour from Salad.
At 720 hours per month, one RTX 2070 costs an estimated $43 at the median on-demand price. Cheapest verified in stock: $43 per month on-demand, $22 spot.
GetDeploying currently tracks RTX 2070 configs from 3 providers. The cheapest verified in-stock on-demand configs come from Salad, Vast.ai and Theta EdgeCloud. 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 2070'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.
8GB GDDR6 with Turing Tensor Cores. Budget option for basic compute tasks.
8GB VRAM and no NVLink. Very limited for AI workloads. Newer budget GPUs are a much better value.
Nvidia RTX 3070
8 GB GDDR6 · released Q4 2020
Nvidia RTX 2080
8 GB GDDR6 · NVLink 50 GB/s
Nvidia RTX 2060 Super
8 GB GDDR6 · released Q3 2019
Last updated
