# Private model serving and fine-tuning: plan quality and capacity

Enclave runs open or custom models on GPUs in your cloud. Compare model quality, workload utilization and operational responsibility before replacing a hosted endpoint.

## Relevant capabilities

- Model serving and fine-tuning on customer GPUs
- pgvector retrieval and governed data access
- Eligible endpoints can scale down when idle

## How to compare

- Does the chosen model meet the actual quality and safety requirements?
- What capacity and cold-start trade-offs suit the traffic?
- Which data, models and licenses can run in the selected region?

## Bring these inputs

- Model and representative evaluation set
- Traffic, context length and latency profile
- Region, licenses and available GPU capacity

## A practical first workflow

- Define the quality and latency acceptance bar.
- Pilot one endpoint with representative traffic and retrieval needs.
- Compare utilization and total cost, then agree the production operating model.

## Check before expanding

- Evaluate answer quality on the agreed cases.
- Measure startup, latency and capacity under load.
- Include idle compute, storage and support in cost comparisons.

## Economics
Compare the cloud bill, platform charges, operating effort and migration work for the same workload. Cloud capacity is not free. Charges and scope need agreement before paid deployment.

## Switching considerations
AWS and Google Cloud are available today; other deployment environments are roadmap. Preserve the existing workload and access path until compatibility, recovery and cutover checks pass.

## Free next step
Get a free deployment checklist, then create your workspace. Free expert help with your use case is also available through our contact form.

[Create your HyperLake workspace](https://app.hyperlake.cloud/users/sign_in?intent=private-model-serving&offer_id=starter-checklist-v1&utm_source=hyperlake&utm_medium=owned&utm_campaign=signup-journey&utm_content=landing_hero)

[Download the free checklist](https://hyperlake.cloud/solutions/private-model-serving.txt)

No free cloud capacity is promised. Deployment scope and charges are agreed separately; AWS and Google Cloud are available today.

## Sources
- https://hyperlake.cloud/stacks
- https://hyperlake.cloud/faq
- https://hyperlake.cloud/get-started

[Discuss this workload](https://hyperlake.cloud/contact)