Quira Quira Docs
GitHub Star

Local AI

The Context Graph captures your browsing structure. The Local AI is what makes it intelligent. Quira ships with a local LLM that runs entirely on-device. It powers page summarization, entity extraction, embedding generation, and  Emost importantly  Enatural language queries against your Context Graph. No data ever leaves your device by default (see AI Privacy Levels).

Model options

ConfigModelParametersMin RAMUse Case
DefaultPhi-3.5 Mini3.8B8 GBStandard summarization, entity extraction, NL Query
OptionalLlama 3.1 8B Q48B (4-bit)16 GBHigher quality responses, deeper reasoning

Runtime by platform

PlatformRuntimeAcceleration
macOS (Apple Silicon)MLXMetal GPU
macOS (Intel)llama.cppCPU
Linuxllama.cppCUDA / Vulkan / CPU

AI Shield privacy indicator

  • Green Shield (LOCAL) EAll AI processing on-device. This is the default.
  • Purple Shield (CLOUD) ECloud AI is active (opt-in only). Heavy tasks offloaded to cloud.

First-run model download

  1. Launch Quira for the first time EA model download prompt appears with estimated size (~2.3 GB) and time.
  2. Background download EProgress bar with percentage and ETA. You can browse normally during the download.
  3. Ready notification E"Your local AI is ready"  Eall AI features are now active.
← Previous: Context Spaces Next: Research Replay →
Was this page helpful?
Ask AI
Q

Ask anything about the documentation

Ctrl+K to open anytime