Store › model › Embeddings

nomic-embed-text-v2-moe-GGUF

Name: nomic-embed-text-v2-moe-GGUF
Author: nomic-ai

by nomic-ai · source Hugging Face · updated 2025-05-15

apache-2.0328 MB~1 GB RAMsource aliveunlabeled

Llama.cpp Quantizations of nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:nomic-ai/nomic-embed-text-v2-moe-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe-GGUF
License: apache-2.0
Requirements: about 1 GB of RAM, 328 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
Tags: gguf sentence-similarity feature-extraction en es fr de it pt pl nl tr ja vi ru id

Numbers

41,740 downloads on Hugging Face
80 likes
license apache-2.0
0.3 GB for nomic-embed-text-v2-moe.Q4_K_M.gguf
4,402,710 npm downloads a week for @huggingface/transformers
latest @huggingface/transformers@4.3.0

Numbers as of 2026-10-02 20:53 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`nomic-embed-text-v2-moe.Q2_K.gguf`	Q2_K	261 MB
`nomic-embed-text-v2-moe.Q3_K_L.gguf`	Q3_K_L	307 MB
`nomic-embed-text-v2-moe.Q3_K_M.gguf`	Q3_K_M	294 MB
`nomic-embed-text-v2-moe.Q3_K_S.gguf`	Q3_K_S	275 MB
`nomic-embed-text-v2-moe.Q4_0.gguf`	Q4_0	309 MB
`nomic-embed-text-v2-moe.Q4_1.gguf`	Q4_1	326 MB
`nomic-embed-text-v2-moe.Q4_K_M.gguf`	Q4_K_M	328 MB
`nomic-embed-text-v2-moe.Q4_K_S.gguf`	Q4_K_S	310 MB
`nomic-embed-text-v2-moe.Q5_K_M.gguf`	Q5_K_M	354 MB
`nomic-embed-text-v2-moe.Q5_K_S.gguf`	Q5_K_S	343 MB
`nomic-embed-text-v2-moe.Q6_K.gguf`	Q6_K	379 MB
`nomic-embed-text-v2-moe.Q8_0.gguf`	Q8_0	488 MB
`nomic-embed-text-v2-moe.bf16.gguf`	BF16	913 MB
`nomic-embed-text-v2-moe.f16.gguf`	F16	913 MB
`nomic-embed-text-v2-moe.f32.gguf`	F32	1.8 GB

From the source README

Llama.cpp Quantizations of nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings

Blog | Technical Report | AWS SageMaker | Atlas Embedding and Unstructured Data Analytics Platform

This model was presented in the paper Training Sparse Mixture Of Experts Text Embedding Models.

Using llama.cpp commit e3a9421b7 for quantization.

Original model: nomic-embed-text-v2-moe

Usage

This model can be used with the llama.cpp server and other software that supports llama.cpp embedding models.

Embedding text with `nomic-embed-text` requires task instruction prefixes at the beginning of each string.

For example, the code below shows how to use the `search_query` prefix to embed user questions, e.g. in a RAG application.

Start a llama.cpp server:
```
llama-server -m nomic-embed-text-v2-moe.bf16.gguf --embeddings
```

And run this code:
```python
import requests

def dot(va, vb):
return sum(a * b for a, b in zip(va, vb))

Card id model:hf:nomic-ai/nomic-embed-text-v2-moe-GGUF · collected 2026-10-02 20:53 UTC · JSON