[Models](/models)/nvidia/Nemotron-3-Embed-8B-BF16

NVIDIA Open Model License

# Nemotron-3-Embed-8B-BF16

by nvidia

8B text embedding model aimed at retrieval and RAG rather than classification

8Bparams

[HuggingFace](https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`nvidia/Nemotron-3-Embed-8B-BF16`

## Deploy Nemotron-3-Embed-8B-BF16

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

This is a retrieval-first text embedding model. The card tags it for text-embeddings, retrieval, semantic-search and RAG, and ships it in a sentence-transformers layout with vLLM support, which tells you what it is meant to sit inside.

Size is the tradeoff to think about. At 8B parameters this is roughly two orders of magnitude larger than the MiniLM-class encoders most pipelines start with, and it will not be the thing you run over a hundred million chunks. It is the thing you run when recall on hard queries matters more than throughput, or as a reranking stage behind a cheaper first pass.

A 1B variant exists in the same family if this does not fit the budget.

## Architecture

Ministral3Model, 7,952,683,008 parameters, BF16 weights. Sentence-similarity pipeline packaged for sentence-transformers and vLLM.

## Mixpeek SDK Integration

IngestRetrieve

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so Nemotron-3-Embed-8B-BF16 runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace\_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns\_your\_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API\_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection\_id: "col\_your\_collection",
      documents: \[
        {
          document\_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "text-embedding": yourVector },
          payload: { source\_key: "archive/2026/asset-00412" },
        },
      \],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// text\_extractor@v1 runs intfloat/multilingual-e5-large-instruct
// (1024-d) over a bucket, with no inference of your own.

## Capabilities

*   Dense text embeddings for semantic search
*   Retrieval over document chunks for RAG
*   Reranking a candidate set from a smaller encoder
*   Served through vLLM for batched throughput

## Use Cases on Mixpeek

The text half of a multimodal index, alongside an image or video encoder

High-recall retrieval where a small encoder keeps missing the right chunk

Second-stage reranking behind a fast first-pass embedding

Grounding an agent's answers in your own documents

## Explore on Mixpeek

[

Browse all models

Search the full model catalog

](/models)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

Organizationnvidia

Retriever\-

Parameters8B

LicenseNVIDIA Open Model License

Downloads/moN/A

### Build a pipeline with Nemotron-3-Embed-8B-BF16

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)