AGAnchorGPU
NVIDIAIn stock

Rent RTX 4090 GPU

A dedicated NVIDIA RTX 4090 with 24 GB GDDR6X, 16 vCPU, 128 GB system RAM, and 2 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 409024 GB$110$3900%
2× RTX 409048 GB$209$7415%
4× RTX 409096 GB$405$1,4358%
8× RTX 4090192 GB$792$2,80810%

Regional inventory

Three regions in the catalog.

DallasTexas · US-TX-1
360cards in catalog
AshburnVirginia · US-VA-1
145cards in catalog
PortlandOregon · US-OR-1
85cards 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 4090.

Good starting point

A 24 GB starting point for an image-generation or video workflow whose model and intermediates have already been shown to fit.

Your catalog configuration pairs 24 GB GPU memory with 128 GB host RAM and 2 TB local NVMe per card.

Before choosing the term

Higher resolution, more frames or larger batches can change the memory requirement substantially. Use the same settings when comparing alternatives.

Use $110 for a 7-day pilot, or $390 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