Use case
Text embeddings.
Embedding models convert text into fixed-length vectors that capture semantic meaning. The bedrock of every RAG pipeline, vector database, and semantic-search system. Most embedding models are tiny enough to run on consumer GPUs or even CPU.
≥ 2GB VRAM
Consumer tier
Best GPUs
Top GPUs for this workload.
Ranked by suitability — higher fitness scores mean the card handles this workload more comfortably.
No GPU recommendations linked to this workload yet.
Best AI models
0B
0B
1B
Top models for this workload.
Nomic Embed Text
by Nomic AI
· Nomic Embed
· 8,192 ctx
Open embedding model — 69M Ollama pulls, the local default.
mxbai-embed-large
by Mixedbread AI
· Mixedbread Embed
· 512 ctx
335M embedding model — top MTEB scores for its size.
BGE-M3
by BAAI (Beijing Academy of AI)
· BGE
· 8,192 ctx
Multilingual + multifunctional embedding (100+ languages).