MLX-quantized (4-bit, affine, group size 64) conversion of Microsoft's microsoft/harrier-oss-v1-27b — a state-of-the-art multilingual text embedding model (released March 2026) built on a Gemma3 decoder-only backbone with last-token pooling and L2 normalization.

This checkpoint is optimized for Apple Silicon via MLX and the mlx-embeddings runtime.

The base model reports MTEB v2 = 74.3 (see the upstream model card); quantized variants are expected to be close to this but have not been independently re-evaluated.

Converted with mlx_embeddings.convert:

Harrier-OSS-v1 uses a plain [Transformer, Pooling, Normalize] SentenceTransformer pipeline (no Dense projection head in modules.json), but the upstream mlx_embeddings.models.gemma3_text.Model class unconditionally expects dense.0.weight / dense.1.weight parameters. A small install-local patch was applied to gemma3_text.py so that the dense heads are treated as optional: if the source checkpoint has no dense.* weights, self.dense is replaced with [] during sanitize(), and the forward pass's for dense in self.dense: ... loop becomes a no-op. The patched file will be contributed upstream.

The base model was trained with instruction-style prompts for retrieval (web_search_query), STS (sts_query), and bitext mining (bitext_query). See config_sentence_transformers.json in this repo for the exact prefixes.

Multilingual (100+ languages). See the upstream model card for the full list.