Models

EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.

EmbeddingGemma is a 300M parameter embedding model from Google.

nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

A high-performing open embedding model with a large token context window.

Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes

State-of-the-art large embedding model from mixedbread.ai

Embedding models on very large sentence level datasets.

A suite of text embedding models by Snowflake, optimized for performance.

Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.

The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.

Embedding model from BAAI mapping texts to vectors.

Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

You are an expert AI coding assistant optimized for GitHub Copilot workflows. Provide clean, concise, efficient, and syntactically correct code. Avoid unnecessary conversational filler or explanations unless explicitly requested.

Nemotron-3.5-Embed 1B and 8B: multilingual text + image embedding models for retrieval and RAG. 32,768 tokens context, 34 languages, bundled vision projector.

Compact text embeddings: 768-dimensional vectors, with a 156.94 MB default and a 182.04 MB alternative. Measured Q4_K_S: nDCG@10 0.859481, Recall@10 0.914856 on BEIR SciFact and FiQA development panel, equal-domain average.

Turkish-first multimodal embeddings (text, images, audio) from Magibu AI, built on EmbeddingGemma 2: 768-d vectors, 8K context.

Multilingual text embedding model built for Hindsight's agent memory. 384 dimensions, truncatable to 256, 128 or 64.

WeMM-Embedding-2B is a universal multimodal embedding model built on Qwen3.5.