Open embedding model — 69M Ollama pulls, the local default.
FAQ
Frequently asked.
How do I run Nomic Embed Text?
Nomic Embed Text is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Nomic Embed Text?
Nomic Embed Text's access providers haven't been catalogued yet on RentGPU. Check the maker's documentation for official endpoints.
How much does it cost to run Nomic Embed Text?
Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.
Is Nomic Embed Text open-source or proprietary?
Nomic Embed Text is open-weight under the Apache-2.0 license. You can download and self-host it.
Description
About Nomic Embed Text.
Nomic Embed Text v1.5 is the most-downloaded open-weight embedding model. 137M parameters, 8K context, outperforms OpenAI's text-embedding-ada-002 on MTEB. Apache-2.0 licensed. Drop-in replacement for any RAG pipeline that wants to leave OpenAI.
Context window
How much it can remember.
8K tokens
≈ 6,144 English words
4K
32K
128K
1M
Capabilities
What it can do.
·
Vision input
·
Audio input
·
Video input
·
Function calling
·
Tool use
·
JSON mode
✓
Streaming
·
Fine-tuning