Harrier Oss V1 0.6B
Developed by Microsoft, Harrier Oss V 1 0.6B is a multilingual text embedding model that excels at tasks such as retrieval, clustering, and semantic similarity. It utilizes a decoder-only architecture with last-token pooling and L2 normalization to produce dense text embeddings.
Input
Output
Context
33K
Max Output
-
Parameters
596M
Technical Specifications
Model TypeEmbedding
Context Window32,768 tokens
Max Output TokensNot available
Parameters596M
Release DateMar 30, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Embedding
Capabilities
Resources & Links
Estimated GPU Requirements for Harrier Oss V1 0.6B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.