Minimum viable Turing GPU for learning CUDA.
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.
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 2060 has 6 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 2060s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
4
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
5
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
13
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
34
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
45
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
57
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
287
|
–
|
–
|
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. How we estimate costs.
Nvidia RTX 2060 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 25.8 TFLOPS |
| INT8 | 103.2 TOPS |
| FP32 | 6.5 TFLOPS |
| Precision support | FP16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 6 GB GDDR6 |
| Bandwidth | 336 GB/s |
| Bus width | 192-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Turing |
| Process | TSMC 12 nm FFN |
| Transistors | 10.8 billion |
| Shader cores | 1,920 CUDA cores |
| Matrix cores | 240 Tensor cores |
| Compute units | 30 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 3.0 x16 |
| Power | |
|---|---|
| Board power | 160 W |
| Cooling | Active |
Source: official Nvidia RTX 2060 datasheet.
As of September 13, 2026, we track 24 configs from 3 providers. Prices are per GPU per hour.
| Billing type | Configs | Cheapest |
|---|---|---|
On-demand | 7 | $0.05 (in stock, Salad) |
Reserved | 10 | $0.17 (24 mo) |
Spot | 7 | $0.02 (in stock, Salad) |
No median for on-demand, reserved and spot: we only show this when at least 3 providers list the GPU on that billing type.
The cheapest verified in-stock estimate is $36 per month on-demand, $461 reserved, $14 spot.
GetDeploying currently tracks RTX 2060 configs from 3 providers. Salad and Vast.ai 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 2060'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.
6GB GDDR6 with basic Turing Tensor Cores. Extremely affordable for learning GPU programming.
Only 6GB VRAM, which limits most AI model loading. Better suited for learning CUDA fundamentals.
Last updated
