Models / multilingual-e5-small / multilingual-e5-small ~118M
Xenova/ multilingual-e5-smallEmbeddings (features) · served with ONNX Runtime · ↓ 472.9K downloads a month · View on Hugging Face
Weights 470 MB
GPU memory needed about 1.7 GB
Memory · disk 8 GB · 30 GB
Licence not stated Versions Smaller versions (8-bit, 4-bit) need less GPU memory and answer a little less precisely.
Versions of multilingual-e5-small ~118M The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
Version Runtime Weights GPU memory Cheapest machine now Original intfloat/multilingual-e5-small Text Embeddings Inference 240 MB 1.8 GB $0.08/h GTX 1660 SUPER Main (Xenova) Xenova/multilingual-e5-small ONNX Runtime 120 MB 1.2 GB $0.08/h GTX 1660 SUPER fra 32768 (alphaedge-ai) alphaedge-ai/multilingual-e5-small-fra-32768 Text Embeddings Inference 70 MB 1.6 GB $0.08/h GTX 1660 SUPER gety embed v0 (gety-ai) gety-ai/gety-embed-v0 ONNX Runtime 120 MB 1.2 GB $0.08/h GTX 1660 SUPER french me5 small (antoinelouis) antoinelouis/french-me5-small Text Embeddings Inference 70 MB 1.6 GB $0.08/h GTX 1660 SUPER rus 32768 (alphaedge-ai) alphaedge-ai/multilingual-e5-small-rus-32768
Hardware and deploy Cheapest GTX 1660 SUPER 6 GB GPU memory from $0.07/h Best value RTX 5090 32 GB GPU memory 117x the speed of the cheapest from $0.67/h Fastest Nvidia B200 179 GB GPU memory 399x the speed of the cheapest from $6.89/h
Choose another machine (54 fit this model)
Deploying ONNX models from the catalog is coming soon. Today, download the files from Hugging Face and upload them in Inference.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.