multilingual-e5-small
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve intfloat/multilingual-e5-smallNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
multilingual-e5-small is an open-weight text embedding model from intfloat, published on Hugging Face in June 2023. It has 120M parameters and is released under the mit license.
HardwareLink to this section
At full FP16 precision the weights need about 1 GB of memory; 8-bit quantization brings that to roughly 1 GB. That is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs.
PopularityLink to this section
multilingual-e5-small had 9,414,953 downloads on Hugging Face in the last month and has 489 likes.
Run it locallyLink to this section
The weights are on Hugging Face and load with sentence-transformers. Follow the model card for the exact setup and license terms.
Frequently asked
Quick answers to common questions
How much VRAM does multilingual-e5-small need?
multilingual-e5-small with 0.12B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is multilingual-e5-small better than other intfloat models?
multilingual-e5-small has 0.12B parameters with 512 context - a strong choice for embeddings.
What license is multilingual-e5-small under?
multilingual-e5-small is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs multilingual-e5-small well?
With 0.12B parameters, multilingual-e5-small requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for multilingual-e5-small?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with multilingual-e5-small?
multilingual-e5-small competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec