# A GPU for models and experiments

> I need an NVIDIA GPU to run or train open models, for an experiment or for a client's system. Nicolas Dao's picks for this job (Cloudless Labs, Sydney), in order of preference, what he would avoid, and what to use instead.

- Use case 4 of 26 in The Stack, last reviewed 9 November 2026
- Web page: https://cloudlesslabs.com/stack/use-cases/gpu/

Picks, in order of preference:

1. **[Runpod](https://cloudlesslabs.com/stack/runpod/index.md)** (My default): Research and experiments: the card you need in minutes, billed per second, stopped at night for the price of its storage.
2. **[SageMaker](https://cloudlesslabs.com/stack/aws-sagemaker/index.md)** (Use when it fits): When the data is the client's: training jobs and endpoints inside its account, Sydney included.
3. **[EC2](https://cloudlesslabs.com/stack/aws-ec2/index.md)** (Use when it fits): A full GPU VM in the client's account, or inference running 24/7 on a Savings Plan.
4. **[Hostinger VPS](https://cloudlesslabs.com/stack/hostinger-vps/index.md)** (My default): The always-on box beside the GPU, for the agents and everything that needs no GPU.

Don't:

- ~~Fargate scheduled tasks~~: Fargate has no GPUs, for tasks or services, and neither has Lambda. Instead: [Runpod](https://cloudlesslabs.com/stack/runpod/index.md) or [SageMaker](https://cloudlesslabs.com/stack/aws-sagemaker/index.md).

Doesn't cover:

- An LLM inside an app: call a model behind an API instead of renting a GPU. That's its own use case: [An AI chat or LLM feature](https://cloudlesslabs.com/stack/use-cases/ai-chat/index.md).

Questions that change the answer:

- Whose data is it? The client's, in its own account or in Australia, means SageMaker or EC2 on AWS.
- Does it run in bursts or 24/7? Bursts point to Runpod, 24/7 to an AWS Savings Plan.
- How much GPU memory does the model need, and does the code expect a full VM (its own Docker, systemd, UDP)? That decides the card, and whether a container will do.

Worked example: [Runpod or AWS for a GPU?](https://cloudlesslabs.com/stack/guides/runpod-or-aws/index.md)

## The picks in brief

- [Runpod](https://cloudlesslabs.com/stack/runpod/index.md): My default. My GPU for research and experiments: the NVIDIA card I need in minutes, billed by the second, stopped at night for the price of its storage. Not the cheapest GPU there is, and a container, not a VM. Pricing: Secure Cloud, per second: RTX 4090 (24 GB) $0.89 an hour, L4 $0.59, RTX A6000 (48 GB) $0.59, L40S $1.09, H100 $3.99. Network volume $0.07 per GB a month, also billed while the pod is stopped. No fees for data in or out. Checked 1 November 2026: Secure prices rose 15–36% between July and October (the 4090 was $0.69), spot pods are retired, and savings plans were withdrawn in October.
- [SageMaker](https://cloudlesslabs.com/stack/aws-sagemaker/index.md): Use when it fits. My AWS answer for GPU work on a client's data: training jobs that bill only while they run, and endpoints that scale, inside the client's account, Sydney included. About 40% over the same EC2 box. Pricing: us-east-1, on demand: ml.g6.xlarge (L4, 24 GB) $1.127 an hour, ml.g6e.xlarge (L40S, 48 GB) $2.61, ml.p5.4xlarge (H100) $7.91; Sydney ml.g6.xlarge $1.465. That's 40% over the same EC2 instance for the 24 and 48 GB cards, and 15% for the H100. Billed per second. SageMaker Savings Plans take up to 64% off. Checked 1 November 2026.
- [EC2](https://cloudlesslabs.com/stack/aws-ec2/index.md): Use when it fits. Servers you run yourself. For GPUs, special hardware or a big steady fleet; for a plain container, Fargate costs the same. Pricing: Sydney, on demand: c7g.large (2 vCPU, 4 GB) $0.0944 an hour, about $68.91 a month; m7g.large (2 vCPU, 8 GB) $0.102 an hour, about $74.46; t4g.small $0.0212 an hour. Fargate on Arm with 2 vCPU and 4 GB is $0.09474 an hour, about the same. Compute Savings Plans take 24% (1 year) to 48% (3 years) off m7g. GPUs (checked 1 November 2026): g6.xlarge (L4, 24 GB) $1.0464 an hour in Sydney, $0.8048 in us-east-1; g6e.xlarge (L40S, 48 GB) $1.861 in us-east-1, not offered in Sydney; p5.4xlarge (one H100) $8.944 in Sydney.
- [Hostinger VPS](https://cloudlesslabs.com/stack/hostinger-vps/index.md): My default. Unbeatable price for an always-on box. CPU caps and no serious GPUs. Pricing: KVM plans from 1 vCPU / 4 GB (KVM 1) to 8 vCPU / 32 GB (KVM 8). Intro prices $6.49 to $25.99 a month paid upfront for the term, renewing at $11.99 to $49.99 a month. Weekly backups and a dedicated IP included.

## Related

- [Runpod or AWS for a GPU?](https://cloudlesslabs.com/stack/guides/runpod-or-aws/index.md): the worked example for this job, with costs
- [Compute](https://cloudlesslabs.com/stack/layers/compute/index.md): every tool in this layer
- [Networking and hosting](https://cloudlesslabs.com/stack/layers/network/index.md): every tool in this layer
- [Every use case and tool in one file](https://cloudlesslabs.com/stack/brief.md)
- [Map of every Markdown file on cloudlesslabs.com, with what each one answers](https://ask.cloudlesslabs.com)