# Harrier — Microsoft's Open-Source Multilingual Embedding Model Family

> Microsoft's Bing team open-sources a decoder-only embedding family that tops the multilingual MTEB-v2 leaderboard.

- Org: Microsoft
- Date: 2026-04-06
- Category: model
- Source: https://blogs.bing.com/search/April-2026/Microsoft-Open-Sources-Industry-Leading-Embedding-Model
- Canonical page: https://ai-tldr.dev/releases/microsoft-harrier-embedding/

## In short

MIT-licensed family of multilingual embedding models (270M, 0.6B, 27B) from Microsoft's Bing team, ranking first on multilingual MTEB-v2 with 32k context and 100+ language support.

## What it is

Harrier-OSS-v1 is a family of three MIT-licensed text embedding models from Microsoft's Bing team. Available in 270M, 600M, and 27B parameter sizes, each model takes text in any of 100+ languages and produces dense vector representations for retrieval, clustering, classification, and semantic similarity. The 27B variant ranks first on the multilingual MTEB-v2 benchmark.

## How it works

Unlike most embedding models that use encoder-only architectures, Harrier is decoder-only with last-token pooling and L2 normalization -- the same transformer family as generative LLMs. This lets it leverage scaling laws that made GPT-class models powerful. All variants share a 32k-token context window and were trained on over 2 billion examples plus synthetic data.

## Why it matters

Embeddings are the foundation of RAG pipelines, semantic search, and agent memory. Having a state-of-the-art multilingual option under MIT license means teams can run retrieval locally without API costs or vendor lock-in. The decoder-only architecture also signals a convergence between embedding and generation model families.

## Who it's for

ML engineers building RAG pipelines, search systems, or agent memory layers.

## Try it

pip install sentence-transformers && model = SentenceTransformer('microsoft/harrier-oss-v1-0.6b')

## Links

- [Announcement](https://blogs.bing.com/search/April-2026/Microsoft-Open-Sources-Industry-Leading-Embedding-Model)
- [Model Card (0.6B)](https://huggingface.co/microsoft/harrier-oss-v1-0.6b)
- [Coverage](https://the-decoder.com/microsofts-bing-team-open-sources-harrier-embedding-model/)