Entry-level Ada Lovelace GPU for prototyping and content creation.
Weekly median price per GPU per hour
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.
USA
3 configs
1x-2x
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 4070 has 12 GB of VRAM. In practice, that's enough memory for roughly 9B parameters at 4-bit or 0.4B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | RTX 4070s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
22 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
7
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
17
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
23
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
29
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
143
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.
Nvidia RTX 4070 · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 116.6 TFLOPS 233.2 with sparsity |
| FP16 / BF16 | 58.3 TFLOPS 116.6 with sparsity |
| INT8 | 233.2 TOPS 466.3 with sparsity |
| FP32 | 29.1 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 12 GB GDDR6X |
| Bandwidth | 504 GB/s |
| Bus width | 192-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Ada Lovelace |
| Process | TSMC 4N |
| Transistors | 35.8 billion |
| Shader cores | 5,888 CUDA cores |
| Matrix cores | 184 Tensor cores |
| Compute units | 46 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 |
| Power | |
|---|---|
| Board power | 200 W |
| Cooling | Active |
Source: official Nvidia RTX 4070 datasheet.
As of September 13, 2026, the median on-demand price is $0.15 per GPU per hour across 3 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 7 | $0.15 | $0.11 (in stock, Vast.ai) |
Spot | 2 | $0.06 (in stock, Vast.ai) |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type.
At 720 hours per month, one RTX 4070 costs an estimated $108 at the median on-demand price. Cheapest verified in stock: $79 per month on-demand, $43 spot.
GetDeploying currently tracks RTX 4070 configs from 3 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, Theta EdgeCloud and Salad. See the full price comparison above for every provider and config.
One RTX 4070 runs models up to roughly 9B parameters at 4-bit quantization or 0.4B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
12GB GDDR6X with Ada Lovelace architecture. Entry-level Ada GPU for basic AI experimentation.
12GB VRAM is insufficient for most LLMs at FP16. Subject to Nvidia's consumer EULA, which may restrict data center use.
Last updated
