Search and RAG

Harrier (harrier-oss)

Microsoft's 2026 multilingual embeddings with context up to 32K tokens; Russian is on the language list. The 270M and 0.6B versions run on a regular server, 27B is the most accurate.

Developer
Microsoft, USA
First release
Mar 2026
Latest release
Mar 2026
Sizes
270M – 27B
License
Commercial use allowedMIT
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting, Legal
Deploy on your server Hugging Face

What it does

  • Multilingual knowledge base search
  • Picking passages for RAG
  • Search across long documents

Where it is used

Customer supportLegal and document managementInternal knowledge bases

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. harrier-oss-v1 (270M, 0.6B, 27B)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Harrier (harrier-oss) be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Harrier (harrier-oss) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Harrier (harrier-oss) support Russian?

Yes, Russian is listed on the model card.

Where can I download Harrier (harrier-oss) and what does it cost?

The Harrier (harrier-oss) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Search and RAGQwen3 Embedding / RerankerAlibaba (Qwen) · ChinaCommercial use allowed

Embeddings and rerankers based on Qwen3, among the best open ones for multilingual search, including Russian. VL versions search images, screenshots and video.

DetailsSearch and RAGE5 / multilingual-e5Microsoft · USACommercial use allowed

Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.

DetailsSearch and RAGEmbeddingGemmaGoogle · USACommercial use with conditions

A small multilingual embedding model based on Gemma 3 that runs even on a phone or laptop without internet.

Details

Source: huggingface.co/microsoft/harrier-oss-v1-27b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.