1 providers · per GPU-hour
NVIDIA RTX 4000 Ada cloud pricing
1 offers from 1 providers, 1 with a published on-demand price. Per GPU-hour, US$. Prices checked 16 Sept 2026.
- Lowest on-demand
- $0.52/GPU-hr
- Lowest spot
- —
- Memory
- 20 GB GDDR6 ECC
Spec sheet: RTX 4000 Ada Generation ↗
| # | Provider | Offer | On-demand | Spot | Committed | As published (original currency) · source | Actions |
|---|---|---|---|---|---|---|---|
| 1 | Akamai Cloud (Linode) | RTX 4000 Ada x1 1× RTX 4000 Ada Generation · 4 vCPU · 16 GB RAM · 500 GB disk | $0.52/GPU-hr | — | — |
What is the RTX 4000 Ada used for?
The RTX 4000 Ada is a workstation-class GPU rather than a data-centre part, built on the Ada Lovelace architecture.
How large a model fits on one RTX 4000 Ada?
With 20 GB of memory, one card holds the weights of a model up to about 10 billion parameters at 16-bit precision, or about 20 billion at 8-bit. That is weights only: inference also needs room for the KV cache, and training needs several times more for gradients and optimiser state, so larger jobs are split across multiple GPUs.
| Spec (as published) | RTX 4000 Ada Generation |
|---|---|
| Architecture | Ada Lovelace |
| Form factor | PCIe single-slot |
| Memory | 20 GB GDDR6 ECC |
| Max power (TDP) | 130 W |
| Precisions listed | FP32 |
| Source | maker spec sheet ↗ |
Need RTX 4000 Ada capacity for a longer run?
Committed and cluster pricing is often negotiated. Tell us the GPU count, duration and region.