Private document search
Semantic search · Retrieval
by Multiple authors
Embeddings.
The quiet index behind an intelligent library: these models turn notes, documents, and snippets into vectors so a local app can find meaning rather than merely match words.
Model makerMultiple authors
Supported in LocalEnginemacOS + iPhone & iPad
Upstream licenseApache-2.0 / MIT
Where it earns its space
Built for a real local rhythm.
These are good-fit starting points—not promises of benchmark performance. Choose the smallest listed option that comfortably covers your work.
Local RAG and retrieval
Finding similar notes or passages
In LocalEngine
Configured variants, by device.
The formats below are the downloads currently represented in LocalEngine’s model catalogs. GGUF runs through the llama.cpp-based runtime; MLX options use the Apple Silicon MLX runtime.
macOS
Qwen3 Embedding 0.6B · Nomic Embed Text v1.5 · BGE Small EN v1.5 · all-MiniLM-L6-v2
- Formats
- GGUF Q4_K_M
- Local note
- Qwen3 is instruction-aware and supports 100+ languages; Nomic is a compact English retrieval choice; BGE and MiniLM emit 384-dimensional English embeddings.
iPhone & iPad
Qwen3 Embedding 0.6B · Nomic Embed Text v1.5 · BGE Small EN v1.5 · all-MiniLM-L6-v2
- Formats
- GGUF Q4_K_M
- Local note
- The same compact retrieval lineup is available on mobile for on-device semantic search.
Model identity, task category, supported formats, and license are based on the linked Hugging Face GGUF sentence-similarity models and the LocalEngine macOS/iOS catalogs. Hardware guidance reflects the packaged variants, not a universal system requirement.