Turing professional GPU for legacy visualization 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.
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 5000 has 16 GB of VRAM. In practice, that's enough memory for roughly 8B 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 5000s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
5
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
108
|
–
|
–
|
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 5000 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 89.2 TFLOPS |
| INT8 | 178.4 TOPS |
| FP32 | 11.2 TFLOPS |
| Precision support | FP16FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR6 |
| Bandwidth | 448 GB/s |
| Bus width | 256-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Turing |
| Process | TSMC 12nm FFN |
| Transistors | 13.6 billion |
| Shader cores | 3,072 CUDA cores |
| Matrix cores | 384 Tensor cores |
| Compute units | 48 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 50 GB/s |
| Host interface | PCIe 3.0 x16 |
| Power | |
|---|---|
| Board power | 265 W |
| Cooling | Active |
Source: official Nvidia RTX 5000 datasheet.
As of September 14, 2026, the median on-demand price is $0.60 per GPU per hour across 3 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 5 | $0.60 | $0.09 (in stock, Vast.ai) |
Spot | 1 | $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 5000 costs an estimated $432 at the median on-demand price. Cheapest verified in stock: $65 per month on-demand, $43 spot.
GetDeploying currently tracks RTX 5000 configs from 3 providers. Vast.ai has verified in-stock on-demand configs. See the full price comparison above for every provider and config.
One RTX 5000 runs models up to roughly 8B 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.
16GB GDDR6 with NVLink (112 GB/s). Turing professional GPU for visualization and moderate compute.
16GB VRAM and Turing architecture are limiting. For AI work, newer Ada Lovelace professional GPUs are a much better choice.
Last updated
