consumer

租用 Nvidia RTX 4090.

Name: Nvidia Nvidia RTX 4090
Brand: Nvidia
SKU: gpu-rtx-4090

Ada Lovelace 24GB VRAM 450W

Price history

Daily median across providers.

Where to rent it

All providers carrying this GPU.

No fresh prices yet.

Workloads

Suitable workloads.

Run LLMs (inference / serving) good Image generation (Stable Diffusion, Flux, …) excellent Video generation good Speech and audio AI good 3D rendering and content creation excellent General ML research and experiments excellent

AI models that fit See all 20 →

Run these on this GPU.

Gemma 3 27B 1× · int4
Llama 3.2 11B Vision 1× · fp16
Qwen 2.5 Coder 32B 1× · fp16

FAQ

Frequently asked.

How is the Nvidia RTX 4090 price calculated?

We pull live listings from each provider's public API, take the median hourly rate across active offers, and refresh every hour. The rate shown is the median, so a single low-ball spot offer can't distort the headline.

Why does the Nvidia RTX 4090 cost different amounts on different providers?

P2P marketplaces like Vast.ai aggregate offers from individual hosts who set their own rates — bidding pushes prices down. First-party clouds (Lambda, hyperscalers) charge a managed-service premium for support, SLAs, and integrated networking. Decentralized networks (io.net, Akash) settle in tokens, which adds volatility but often the lowest base rate.

Can I really train an LLM on a single Nvidia RTX 4090?

Depends on the model size. With 24GB of VRAM you can fine-tune 13B–34B models with LoRA, or run inference on 70B models at int4 quantization.

Spot vs on-demand on the Nvidia RTX 4090 — which should I rent?

On-demand keeps the same instance until you stop it; spot (or interruptible) is cheaper but the host can reclaim it when a higher-paying job lands. Use on-demand for training runs and anything stateful. Use spot for stateless inference, batch jobs, and experiments where a checkpoint every few minutes is enough to recover.

How is hourly billing measured for the Nvidia RTX 4090?

Most providers bill per-second once the instance is running, with a small minimum (often 60 seconds). A handful of first-party clouds round up to the minute. Either way, headline $/hr is the right comparison unit.

Does the region of the host affect the Nvidia RTX 4090 price?

Yes — US and EU regions usually carry a premium over LATAM, India, and parts of APAC, especially on first-party clouds. P2P marketplaces hide this behind one global price because supply moves wherever bids exist.