VectorAIStudio

Supported Models

Supported Models for VectorAIStudio

VectorAI Studio runs models locally in GGUF format via llama.cpp. Popular open-source model families you can download and chat with include:

Supported Model Families

  • Llama for a well-rounded, widely-used general chat model
  • Mistral for fast, efficient responses on modest hardware
  • Phi for a compact model that runs well on lower-end machines
  • Gemma for a lightweight, general-purpose chat model
  • Qwen for strong multilingual and coding performance

All models run in GGUF format, quantized to fit comfortably on typical desktop hardware.

Need More?

Check the FAQ for the latest details on model support and offline behavior.