Search and RAG builders get strong multilingual embeddings free under MIT, from tiny 270M models to a 27B heavyweight.
Kenning's take
What it does
Harrier is a family of open-source text embedding models from Microsoft's Bing team, used to find and rank relevant text for search and AI answers. The largest has 27 billion parameters, with smaller 0.6B and 270M versions for low-end devices, and they support 100+ languages with a 32k context window. The weights are free to download on Hugging Face under the MIT licence.
- Top of multilingual MTEB v2 at launch
- 100+ languages
- 32k token context window
- 27B, 0.6B and 270M sizes
- MIT licence on Hugging Face
Who it suits. Developers building search, retrieval and RAG systems.
Key facts
- Category
- AI models
- Made by
- Microsoft
- Based in
- United States
- Released
- 7 April 2026
- How to get it
- free open weights on Hugging Face
- Works on
- open-weights
- In the UK
- Yes
- Free plan
- yes, open weights
FAQ
Is Harrier free?
Yes. The weights are on Hugging Face under the MIT licence.
When was Harrier released?
Microsoft announced it on 7 April 2026.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.
Cisco Antares
Cisco's small open-weight models that find where known security vulnerabilities sit in a codebase, running locally.