---
license: apache-2.0
tags:
  - vas
  - llama.cpp
  - gguf
  - photography
  - desktop-ai
---

# VAS Pro — AI Models

Pre-quantized GGUF models for VAS Pro (Visual Archive System) local AI assistant.

## Models

| Model | File | Size | Purpose | Original |
|-------|------|------|---------|----------|
| Phi-4 Mini | `phi-4-mini-Q4_K_M.gguf` | ~2.5 GB | Fast responses, greetings | [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) |
| Gemma 3 4B | `gemma-4-4b-it-Q4_K_M.gguf` | ~2.5 GB | Standard tasks, tool calling | [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) |
| Qwen2.5-VL 7B | `qwen3.5-9b-vision-Q4_K_M.gguf` | ~4.7 GB | Vision, OCR, image analysis | [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) |
| MxBAI Embed Large | `mxbai-embed-large-v1-f16.gguf` | ~670 MB | Semantic search embeddings | [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) |

## Usage

These models are automatically downloaded by VAS Pro on first run. No manual setup required.

## Quantization

- Text models use **Q4_K_M** quantization (best quality/size ratio for 4-bit)
- Embedding model uses **F16** (full precision for maximum retrieval accuracy)

## License

Models retain their original licenses:
- Phi-4 Mini: MIT License
- Gemma 3: [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
- Qwen2.5-VL: Apache 2.0
- MxBAI Embed: Apache 2.0