Can You Run BGE-Large Embeddings? Every GPU, Tested

A model that doesn't fit doesn't run slowly, it doesn't run. Here's every card from our bench, sorted by measured speed.

Weights: BAAI/bge-large-en-v1.5

GPUs that run BGE-Large Embeddings (1)

Quick answers

What is the fastest GPU for BGE-Large Embeddings?

NVIDIA L4 is the fastest card we've measured running BGE-Large Embeddings, at 1016.5 sentences/s.

What is the cheapest GPU that can run BGE-Large Embeddings?

NVIDIA L4 ($2,500 MSRP) is the cheapest card on our bench that runs BGE-Large Embeddings, at 1016.5 sentences/s.

← All models · AI GPU rankings · How we benchmark