EmbeddingGemma is a 300M parameter embedding model from Google.
1.8M Pulls 5 Tags Updated 11 months ago
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
3.7M Pulls 12 Tags Updated 11 months ago
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
754.4K Pulls 1 Tag Updated 8 months ago
A high-performing open embedding model with a large token context window.
83M Pulls 3 Tags Updated 2 years ago
State-of-the-art large embedding model from mixedbread.ai
13.7M Pulls 4 Tags Updated 2 years ago
A suite of text embedding models by Snowflake, optimized for performance.
3.1M Pulls 16 Tags Updated 2 years ago
Embedding models on very large sentence level datasets.
3.4M Pulls 10 Tags Updated 2 years ago
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
442.1K Pulls 3 Tags Updated 1 year ago
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.
355.2K Pulls 6 Tags Updated 1 year ago
Embedding model from BAAI mapping texts to vectors.
280.8K Pulls 3 Tags Updated 2 years ago
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
546.9K Pulls 13 Tags Updated 1 year ago
Jarvis Voice’s pinned EmbeddingGemma 300M BF16 artifact: 768-dimensional multilingual embeddings using one immutable model across cloud and local Ollama deployments.
16 Pulls 1 Tag Updated 4 days ago
7 Pulls 1 Tag Updated 5 days ago
Bekko Embedding is an ultra-compact (AP 25m), high-performance multilingual model. Fast on CPUs, with 8K token inputs and 384/256/128/64D outputs.
41 Pulls 4 Tags Updated 2 weeks ago
22 Pulls 3 Tags Updated 2 weeks ago
1,614 Pulls 1 Tag Updated 4 months ago
1,389 Pulls 9 Tags Updated 4 months ago
Bekko Embedding is an ultra-compact (AP 8M), high-performance multilingual model. Fast on CPUs, with 8K token inputs and 384/256/128/64D outputs.
18 Pulls 4 Tags Updated 2 weeks ago
331 Pulls 3 Tags Updated 4 months ago
Qwen embedding model
300 Pulls 4 Tags Updated 3 months ago