Compact entry-level Ada Lovelace workstation GPU for professional visualization.
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-8x
UAE
1 config
1x
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 2000 Ada has 16 GB of VRAM. In practice, that's enough memory for roughly 15B parameters at 4-bit or 2B 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 2000 Adas 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
|
5
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
108
|
–
|
–
|
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 2000 Ada · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 96.0 TFLOPS 191.9 with sparsity |
| FP16 / BF16 | 48.0 TFLOPS 96.0 with sparsity |
| FP32 | 12 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR6 |
| Bandwidth | 224 GB/s |
| Bus width | 128-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ada Lovelace |
| Process | TSMC 4N |
| Transistors | 18.9 billion |
| Shader cores | 2,816 CUDA cores |
| Matrix cores | 88 Tensor cores |
| Compute units | 22 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x8 |
| Power | |
|---|---|
| Board power | 70 W |
| Cooling | Active |
As of September 15, 2026, the median on-demand price is $0.24 per GPU per hour across 3 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 4 | $0.24 | $0.13 (in stock, Theta EdgeCloud) |
Reserved | 1 | On request |
The cheapest verified in-stock on-demand RTX 2000 Ada tracked by GetDeploying is $0.13 per GPU per hour from Theta EdgeCloud.
At 720 hours per month, one RTX 2000 Ada costs an estimated $173 at the median on-demand price. Cheapest verified in stock: $94 per month on-demand.
GetDeploying currently tracks RTX 2000 Ada configs from 3 providers. The cheapest verified in-stock on-demand configs come from Theta EdgeCloud, GPU.ai and Runpod. See the full price comparison above for every provider and config.
One RTX 2000 Ada runs models up to roughly 15B parameters at 4-bit quantization or 2B 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.
Low-power 70W card with ECC memory in a compact dual-slot form factor. Fits small form-factor workstations for CAD, 3D visualization, and light inference tasks.
Limited to PCIe 4.0 x8 bandwidth and 128-bit memory bus. For heavier compute or larger models, consider the RTX 4000 Ada with 20GB and higher throughput.
Last updated
