Perplexity Hybrid Compute Review 2026 — On-Device AI Privacy

Privacy gate on the Mac

A privacy gate on the Mac controls what may leave the machine. Before information from a protected file reaches the cloud, the privacy gate can mask sensitive details, keep it local, refuse the action, or ask for consent.

Sensitive files and information stay on the device.

Cloud and local task split

Hybrid compute divides each task between the cloud and a local model on the Mac. The cloud handles frontier reasoning, web search, and planning, while the local model processes private files, sensitive information, and on-device actions needed at every step.

Computer coordinates the entire workflow, so users never have to split tasks into separate prompts or move information between tools.

On-device Perplexity classifier

The privacy gate includes an on-device Perplexity classifier that identifies sensitive details like names, addresses, account numbers, and secrets before they leave the Mac, and uses those classifications to determine which safeguards to apply. Credentials, payment card numbers, and government IDs receive the strictest protection.

Protected information can be kept local, refused, or rewritten so the cloud model can continue without it.

Organization-wide rules and audits

For Perplexity Enterprise subscribers, admins can set organization-wide rules for what must stay on the Mac, what may be masked before cloud use, and what requires user approval before going to the cloud. Admins can also audit when information leaves a device.

Legal, healthcare, financial, and other teams get a consistent way to use Computer for sensitive work.

Three local models at launch

Hybrid compute on Mac launches with three local models: Gemma 4 E4B, Qwen3.6 35B-A3B, and a Perplexity model. It works on any Apple silicon Mac running macOS 15+ with at least 24GB of unified memory.

A broad range of users can use hybrid inference on the Mac they already own.

Remote access from iPhone

Perplexity Computer works with iPhone. Users can send prompts from anywhere while the local model runs on their Mac, analyzing their most sensitive data privately and entirely on device. Customers who want local inference from anywhere can run Perplexity Computer on a dedicated Mac mini that is always on and can be remotely controlled from the iPhone.

Local inference is accessible from anywhere without moving sensitive data off the Mac.

• Data Privacy on Sensitive DocumentsIts core strength is allowing AI agents to work with confidential files without the data ever leaving the user's Mac, a major advantage for regulated industries.
• User Control and TransparencyThe PII classifier prompts users for action on sensitive data, providing a clear audit trail and control over what is processed where.
• Open-Source Security MechanismOpen-sourcing the PII classifier demonstrates a commitment to transparency, allowing independent security review and building user trust.
• Economic EfficiencyBy processing tokens locally, it reduces the number of billable cloud tokens, offering a cost advantage for users with high-volume, data-sensitive tasks.

• Mac-Only at LaunchThis feature is exclusively for the Mac app with no announced support for Windows or Linux, limiting its utility in mixed-OS organizations.
• High Memory RequirementsA hard memory floor excludes most base-model Macs. There is a discrepancy in reporting: Perplexity states 24GB unified memory, while several outlets report 32GB as required or recommended for larger local models.
• Reduced Local Model CapabilityThe local models are materially smaller and less capable than frontier cloud models, so the quality of output on locally-handled steps will be lower than cloud-only processing.
• Professional RealityThe privacy benefit depends entirely on trusting the local classifier to correctly identify all forms of sensitive data. If it fails, information could be sent to the cloud unintentionally, and the paid-tier requirement adds a cost barrier.

Legal Document Review

A law firm can use the Computer agent to analyze a contract. The local model processes clauses containing privileged information, while the cloud model provides general legal research, ensuring client confidentiality.

Financial Data Analysis

An analyst can instruct the agent to summarize a portfolio's performance. Account numbers and personal client names are handled on-device, while market trends and economic data are researched in the cloud.

Healthcare Record Summarization

A medical administrator can use the agent to draft a summary of a patient's file. The local model processes the patient's name and contact details, while the cloud model assists with formatting and general medical knowledge.

Board Meeting Preparation

An executive assistant can have the agent prepare a briefing document from confidential strategy files. The local model handles the sensitive corporate data, and the cloud model helps structure the final report.

Ensure you have an Apple silicon Mac with macOS 15 or later and at least 24GB of unified memory (32GB is recommended for larger local models).

Subscribe to a paid Perplexity plan (Pro, Max, or Enterprise) to unlock the Hybrid Compute feature in the Mac app.

In the Mac app, navigate to the settings for the Computer agent and select your preferred local model from the supported list (e.g., Gemma E4B, Qwen3.6 35B-A3B, or PPLX Qwen 3.8 27B).

Start a task with the Computer agent; when the local PII classifier detects sensitive information, choose to keep it on-device, mask it, or send it to the cloud.