LiquidAI/Embeddings
Liquid AI's LFM2.5 encoder targets fast CPU inference
A 230M-parameter bidirectional encoder built for long-context English and German embeddings without a GPU.
Category · other
Latest Embeddings models
Open embedding models that turn text and images into vectors — the retrieval and semantic-search backbone of self-hosted RAG and recommendation systems.
5 releases
LiquidAI/Embeddings
Liquid AI ships a 350M encoder built for CPUs
The compact LFM2.5 encoder targets fast, long-context text embeddings without a GPU.
NVIDIA/Embeddings
NVIDIA's Nemotron-3-Embed 8B tops RTEB retrieval test
The 8-billion-parameter text embedding model claims the number one overall spot on the RTEB benchmark, with an eye toward agentic retrieval.
NVIDIA/Embeddings
NVIDIA's Nemotron 3 Embed tops the RTEB leaderboard
A compact 1B-parameter text embedding model claims the top overall spot on a retrieval benchmark aimed at reflecting real-world use.
LiquidAI/Embeddings
Liquid AI ships a 350M multilingual embedding model
LFM2.5-Embedding-350M targets retrieval and search workloads on edge hardware, where compact size matters as much as accuracy.