Who should use this model?
- Small local English embedding model for document search, similarity search, clustering, and classification
Choose something else when
- You need multilingual retrieval as a primary requirement.
What hardware makes sense?
The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. Document-search memory also depends on input length, batch size, and the document index; a chat-memory estimate does not confirm that workload.
- CPU only
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 8GB system memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 16GB system memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 32GB system memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 8GB GPU memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 12GB GPU memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- 24GB GPU memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
- Apple unified memory
- A possible starting point with a compressed model and short conversation; check the exact file size.
Model facts that change the decision
- Parameters
- 0.137B
- Input
- Text
- Published context limit
- 8,192 tokens
- Model format
- safetensors · sentence-transformers · transformers · Transformers.js · ONNX · GGUF · Ollama
- Suggested compression
- Q5_K_M for small local footprint with low embedding MSE; Q8_0 for maximum quantized fidelity
- Typical Q4 file
- 0.084GB before runtime and context overhead
- Languages
- English
Using this model for document search
Select this model for the document-search step in an app that supports it. Keep the model that generates answers separate. Check document chunk length and any required query or document prefixes in the model’s instructions.
Changing the embedding model changes the document vectors. Rebuild the document index rather than mixing vectors from different models.
First setup
Download with Ollama
ollama pull nomic-embed-textLM Studio: Use it as an embedding model, not chat
llama.cpp
Use the llama.cpp embedding example with the official GGUF
Conditions that change the answer
- This is an embedding model only; it cannot generate chat responses.
- Ollama's library page lists a 2K context window for its packaged model, while the Nomic model card/docs list 8192 tokens; follow the limit of your chosen app and package.
Read the controlling license text →