Nomic Embed Text v1.5
Nomic AI · Embedding · 137M · 8k context · Released 14 February 2024
Commercial use permitted
Open weights
Runs on CPU
Apple Silicon
A small, fast English-focused embedding model with an 8192-token input, and one of the most common defaults for local RAG. Apache 2.0 and light enough to run comfortably on a CPU.
Strengths
- Very small and fast, runs easily on CPU
- Long 8192-token input for a model this size
- Apache 2.0, and open about its training data and code
Weaknesses
- English-focused, so weaker on multilingual content than BGE-M3
- A general model, so domain-tuned embedders may retrieve better
- Smaller and older than the current top of the retrieval leaderboards
Hardware requirements
| Quantisation | Approx. VRAM | Notes |
|---|---|---|
| FP16 | ~0.3GB | Full precision, trivial to run on CPU or any GPU |
Also runs on CPU (slower). Optimised builds available for Apple Silicon.
Licence
Apache 2.0 — read the licence
Availability
- Official page
- Hugging Face
- ollama run nomic-embed-text
Recommended for
- A lightweight default embedder for English RAG
- CPU-only or memory-constrained setups
- Getting a retrieval system working quickly
Run it with
Catalogue entry last verified 30 July 2026. Specifications change; verify anything you are about to spend money on.