Customer-managed
Deploy Pūnaha in an environment controlled by the customer, with the surrounding infrastructure and operations agreed for that implementation.
Private AI deployment
Run enterprise AI where your data and operations require it
Pūnaha can run on customer-controlled infrastructure or in Pūnaha Cloud. Connect supported local and external models so deployment and model choices reflect the work, risk and environment.
Your infrastructure
Pūnaha
Your model choices
Deployment choice
One product, two operating approaches
Choose the approach that fits the organisation rather than reshaping every requirement around a cloud-only service.
Pūnaha Cloud
Use a Pūnaha-managed cloud option when that operating model is a better fit.
Windows and Linux
The application supports Windows and Linux environments, subject to the implementation architecture.
Model choice
Use the model that fits each task
A model deployment is configured separately from the workflow that uses it, which makes the relationship easier to change and govern.
Local GGUF models
Run supported GGUF models locally through llama.cpp for tasks intended to stay within the local environment.
OpenAI and compatible APIs
Connect OpenAI or a supported OpenAI-compatible endpoint when that service fits the use case.
Azure OpenAI
Configure Azure OpenAI deployments as an external model option.
Anthropic
Use supported Anthropic models for selected workflow steps.
Google Gemini
Connect supported Gemini models where their capabilities and service terms fit.
Provider-neutral configuration
Refer to configured model deployments from workflows rather than embedding one provider into every process.
Clear boundaries
Private AI still needs deliberate architecture
Deployment location is one part of privacy and control, not a substitute for them.
Source permissions, network paths, model endpoints, operational access and retention choices all shape the resulting control boundary.
Pūnaha provides deployment and model options. Each implementation still needs an agreed architecture and security review that reflects the organisation's requirements.
Data path
Understand which sources, services and models can receive content at each step.
Operational ownership
Decide who runs, monitors and changes the deployment.
Human oversight
Add approval where automated continuation is not appropriate.
Private AI deployment questions
Does Pūnaha have to run in Pūnaha Cloud?
No. Pūnaha can run on customer-controlled infrastructure or in Pūnaha Cloud. The appropriate option depends on the customer's environment and operating requirements.
Can Pūnaha use a local AI model?
Yes. Pūnaha supports local GGUF model execution through llama.cpp as well as supported external model providers.
Can one workflow use more than one AI provider?
Yes. Different workflow steps can refer to different configured model deployments when the process calls for it.
Is Pūnaha described as air-gapped?
No broad air-gap claim is made on this site. A customer-managed implementation can use local models, but the complete architecture must be reviewed for the specific environment.
Discuss the environment you need to support
We can walk through deployment, model and workflow choices in a private technical demonstration.