Nomic Embed
Top pickThe sovereign default — Apache-2.0, one command in Ollama, up to 8k context with rotary scaling.
92
sovereigntynomic-embed-text-v1.5 is the open model that made local embeddings boring: Apache-2.0 with the training recipe published, Matryoshka dimensions to trade size for speed, and one-command serving through Ollama on hardware you already own. Its context is 2,048 tokens by default and scales to 8,192 with dynamic rotary scaling switched on — Ollama's build stops at 2K, so chunk to fit.
OPEN SOURCEApache-2.0SELF-HOSTLOCAL-FIRST
LicenseApache-2.0
PricingFree — runs locally via Ollama or sentence-transformers; your hardware is the cost
Open sourceYes
Self-hostableYes
Local-first dataYes
What it does well
- +Truly open: Apache-2.0 including the training recipe
- +Up to 8,192 tokens with rotary scaling — 2,048 by default
- +One-command local serving through Ollama, CPU-friendly
Where it falls short
- −English-focused — the multilingual variant is weaker
- −You own the serving and monitoring
- −Benchmark ceiling sits below the premium hosted models
Nomic Embed as an alternative to
Where Nomic Embed shows up in our comparisons, and how it ranked.
Nomic Embed head-to-head
Straight comparisons against the tools people weigh it against.