Popular legacy consumer GPU for local AI development with NVLink.
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 3090 has 24 GB of VRAM. In practice, that's enough memory for roughly 21B parameters at 4-bit or 6B 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 3090s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
$0.24
|
$173
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
$0.48
|
$346
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
4
|
$0.96
|
$691
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
9
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
12
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
15
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
72
|
–
|
–
|
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 3090 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 71.2 TFLOPS 142.4 with sparsity |
| INT8 | 284.7 TOPS 569.4 with sparsity |
| FP32 | 35.6 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 24 GB GDDR6X |
| Bandwidth | 936 GB/s |
| Bus width | 384-bit |
| ECC | No |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 28.3 billion |
| Shader cores | 10,496 CUDA cores |
| Matrix cores | 328 Tensor cores |
| Compute units | 82 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 112 GB/s |
| Host interface | PCIe 4.0 |
| Power | |
|---|---|
| Board power | 350 W |
| Cooling | Active |
Source: official Nvidia RTX 3090 datasheet.
As of October 3, 2026, the median on-demand price is $0.24 per GPU per hour across 10 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 57 | $0.24 | $0.10 (in stock, HyperAI) |
Reserved | 49 | $0.06 (1 mo, in stock, HyperAI) |
|
Spot | 36 | $0.05 (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 3090 costs an estimated $173 at the median on-demand price. Cheapest verified in stock: $72 per month on-demand, $43 reserved (1 mo), $36 spot.
GetDeploying currently tracks RTX 3090 configs from 10 providers. The cheapest verified in-stock on-demand configs come from HyperAI, Vast.ai, GPU.ai and Lium. See the full price comparison above for every provider and config.
One RTX 3090 runs models up to roughly 21B parameters at 4-bit quantization or 6B 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.
24GB GDDR6X with NVLink support (112 GB/s). One of few consumer GPUs supporting NVLink for 2-GPU configurations. Popular legacy choice for AI researchers.
Nvidia RTX 5090
32 GB GDDR7 · 91% more bandwidth than the RTX 3090
Nvidia RTX 4090
24 GB GDDR6X · PCIe only
Nvidia RTX 3090 Ti
24 GB GDDR6X · PCIe only
Last updated
