Runpod
Our sponsor- On-Demand
- from $0.20
- Reserved
- on request
Single-slot professional card for desktop AI, rendering, and compute workloads.
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.
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 4000 Ada has 20 GB of VRAM. In practice, that's enough memory for roughly 22B parameters at 4-bit or 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 4000 Adas needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
|
|
18 GB
|
1
|
$0.24
|
$173
|
|
|
22 GB
|
2
|
$0.48
|
$346
|
|
|
67 GB
|
4
|
$0.96
|
$691
|
|
|
178 GB
|
10
|
–
|
–
|
|
|
239 GB
|
14
|
–
|
–
|
|
|
306 GB
|
17
|
–
|
–
|
|
|
1,544 GB
|
86
|
–
|
–
|
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 4000 Ada · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 213.8 TFLOPS 427.6 with sparsity |
| FP16 / BF16 | 106.9 TFLOPS 213.8 with sparsity |
| FP32 | 26.7 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 20 GB GDDR6 |
| Bandwidth | 360 GB/s |
| Bus width | 160-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ada Lovelace |
| Process | TSMC 4N |
| Transistors | 35.8 billion |
| Shader cores | 6,144 CUDA cores |
| Matrix cores | 192 Tensor cores |
| Compute units | 48 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 130 W |
| Cooling | Active |
As of September 17, 2026, the median on-demand price is $0.24 per GPU per hour across 5 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 18 | $0.24 | $0.20 (in stock, GPU.ai) |
Reserved | 7 | $0.19 (3 mo, in stock, Vast.ai) |
|
Spot | 4 | $0.15 (in stock, Vast.ai) |
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 4000 Ada costs an estimated $173 at the median on-demand price. Cheapest verified in stock: $144 per month on-demand, $137 reserved (3 mo), $108 spot.
GetDeploying currently tracks RTX 4000 Ada configs from 6 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Runpod and Vast.ai. See the full price comparison above for every provider and config.
One RTX 4000 Ada runs models up to roughly 22B parameters at 4-bit quantization or 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.
20GB GDDR6 with ECC in a single-slot, 130W card, so it fits workstations and dense chassis that cannot take a dual-slot GPU. Ada Lovelace FP8 Tensor Cores cover AI development alongside rendering and viewport work.
20GB limits the model sizes you can hold in memory, and there is no NVLink to pool across cards. Step up to the RTX 4500 Ada for 24GB or the RTX 6000 Ada for 48GB when the model does not fit.
Last updated