Embedding335M official

mxbai-embed-large

by Mixedbread AI

A state-of-the-art large embedding model for English retrieval and semantic search.

arcflare run mxbai-embed-large

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

A strong English embedding model from Mixedbread AI, great for RAG and search.

arcflare run mxbai-embed-large

[ 03 ] // relatedmore →

Alibaba Qwen

Qwen3-Embedding: multilingual text and code embeddings at 0.6B, 4B and 8B, near the top of the MTEB leaderboard.

4% of a 24 GB card

#embedding #retrieval #multilingual

Nomic AI

English text embedding model with Matryoshka representation learning for resizable embeddings; requires task instruction prefixes.

8% of a 24 GB card

#embedding #small

Nomic AI

Multilingual mixture-of-experts text embedding model (475M total, 305M active) supporting about 100 languages with Matryoshka embeddings.

8% of a 24 GB card

#embedding #small