AGAnchorGPU
NVIDIAIn stock

Rent RTX 3090 GPU

A dedicated NVIDIA RTX 3090 with 24 GB GDDR6X, 12 vCPU, 96 GB system RAM, and 1 TB local NVMe per card.

Node pricing

One price for the whole period.

The product model allocates each GPU to one account for the complete term. Adding cards to a node applies the catalog volume discount to every card.

NodeTotal VRAM7 days30 daysDiscount
1× RTX 309024 GB$52$1840%
2× RTX 309048 GB$99$3505%
4× RTX 309096 GB$191$6778%
8× RTX 3090192 GB$374$1,32510%

Regional inventory

Three regions in the catalog.

DallasTexas · US-TX-1
150cards in catalog
AshburnVirginia · US-VA-1
60cards in catalog
PortlandOregon · US-OR-1
35cards in catalog

Ready-to-run images

Start with your stack installed.

Ubuntu 24.04CUDA readyPyTorch 2.8CUDA 12.8vLLMOpenAI-compatible APIComfyUIFlux & SDXLOllamaLocal model serverJAXCUDA 12Debian 13Minimal

Workload fit

When to consider RTX 3090.

Good starting point

A budget-oriented 24 GB development configuration for reproducible prototypes and image-generation experiments.

Your catalog configuration pairs 24 GB GPU memory with 96 GB host RAM and 1 TB local NVMe per card.

Before choosing the term

Check that the full pipeline fits without excessive offload. If memory is the limit, compare a 48 GB card instead of assuming another 24 GB card fixes it.

Use $52 for a 7-day pilot, or $184 for a 30-day allocation after validating the workload. Options are additional.

Optional resources

Add only what the node needs.

Options are billed for the same fixed term as the GPU node.

Extra NVMe storage1 TB / period

$9 / week $29 / month

Dedicated public IPv4address / period

$3 / week $10 / month

Extra bandwidth10 TB / period

$12 / week $39 / month

Private colocation VLANnode / period

$25 / week $85 / month