Nomic Embed Text is a quantized GGUF version of a text embedding model hosted on Hugging Face. It belongs to the class of foundation models and carries the tasks of sentence similarity and feature extraction. The model is provided under the Apache 2.0 license.
It is delivered as files that run with llama.cpp and the llama-cpp-python library. Users install llama-cpp-python via pip and load the model by specifying the repository nomic-ai/nomic-embed-text-v1.5-GGUF together with a chosen quantized filename such as nomic-embed-text-v1.5.Q2_K.gguf. The same repository can be used directly with the llama.cpp command-line tools on macOS and Linux. Commands include starting a local OpenAI-compatible server with a web UI or running inference from the terminal.
The model was created by Nomic AI. It has been liked 121 times on Hugging Face and the organization maintains 1.18k followers there. No pricing information appears for the model itself because it is distributed as an open-source artifact under the stated license.
In the Embeddings & retrieval space, Nomic Embed Text takes a focused approach. It focuses on generating high-quality text embeddings locally for semantic search and RAG applications without cloud APIs. It is built as an open-source project for developers. The project is open source (MIT). It ships for the web, the command line, and embeddable surfaces, and it can be self-hosted.
Behind Nomic Embed Text is Nomic AI, and it first shipped in 2023. Development happens publicly on GitHub with 121.2k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 5 similar projects. Among its 4 catalogued features are text embeddings, GGUF format, and local inference. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do