Entry-level Ampere GPU for learning GPU programming.
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 3070 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 3070s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
4
|
$0.44
|
$317
|
Gemma 4 31B
30.7B
|
24 GB
|
4
|
$0.44
|
$317
|
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 3070 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 40.6 TFLOPS 81.3 with sparsity |
| INT8 | 162.6 TOPS 325.2 with sparsity |
| FP32 | 20.3 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 8 GB GDDR6 |
| Bandwidth | 448 GB/s |
| Bus width | 256-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 17.4 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 | 220 W |
| Cooling | Active |
Source: official Nvidia RTX 3070 datasheet.
As of October 3, 2026, the median on-demand price is $0.11 per GPU per hour across 3 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 19 | $0.11 | $0.08 (in stock, Vast.ai) |
Reserved | 5 | $0.09 (1 mo, in stock, Vast.ai) |
|
Spot | 13 | $0.04 |
No median for reserved and spot: we only show this when at least 3 providers list the GPU on that billing type.
At 720 hours per month, one RTX 3070 costs an estimated $79 at the median on-demand price. Cheapest verified in stock: $58 per month on-demand, $65 reserved (1 mo), $43 spot.
GetDeploying currently tracks RTX 3070 configs from 3 providers. Vast.ai and Runpod have 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 3070'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 Ampere Tensor Cores. Low-cost entry point for learning GPU computing and basic inference.
8GB VRAM is insufficient for most AI models at FP16. Better suited for learning and prototyping than production use.
Nvidia RTX 4070
12 GB GDDR6X · released Q2 2023
Nvidia RTX 3060 Ti
8 GB GDDR6 · released Q4 2020
Nvidia RTX 3070 Ti
8 GB GDDR6X · 36% more bandwidth than the RTX 3070
Last updated
