multilingual-e5-large
intfloatmittext

multilingual-e5-large

Updated Nov 21, 2026
Parameters
560M
License
mit
Q4 GGUF
0.41 GB
Updated
Nov 21, 2026

Q4 GGUF download: Ralriki/multilingual-e5-large-instruct-GGUF - 0.41 GB on disk, read 2026-11-19. VRAM figures above are estimates; this is the actual file size.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit multilingual-e5-large with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
1 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve intfloat/multilingual-e5-large

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

multilingual-e5-large is an open-weight text embedding model published by intfloat on Hugging Face in June 2023, with 560M parameters under the mit license.

Among the 19 text embedding models in this directory it ranks 9th by monthly Hugging Face downloads, and 6 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.

Similar text embedding modelsLink to this section

PopularityLink to this section

multilingual-e5-large was downloaded 7,318,858 times on Hugging Face in the last month (124,005,192 all-time) and has 1,290 likes.

Run it locallyLink to this section

Weights and usage instructions are on the intfloat/multilingual-e5-large model card; it loads with sentence-transformers.

Local runtimes that fit this model:

  • transformers - the reference Python library most model cards target

PaperLink to this section

From the community

What users are saying

“Hi @Ziizu , Thanks for the interest in this model. About your questions: 1. How should I go through the fine-tuning process, do you recommend that I go through pre-training + fine-tuning or just do fine-tuning? The multilingual-e5- models have already gone through extensive multilingual pre-training.”

“Hello, I used transformers library of intfloat/multilingual-e5-large this model. I used the same code that is shared in its model card. I dockerized it and started to use. It increases the memory in each inference and then it exceeding my memory limit after a while.”

“Hey, I just ran the numbers on 10 semantic textual similarity tasks with multilingual-e5-large.”

Frequently asked

Quick answers to common questions

How much VRAM does multilingual-e5-large need?

multilingual-e5-large with 560M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is multilingual-e5-large better than other intfloat models?

multilingual-e5-large has 560M parameters - a strong choice for embeddings.

What license is multilingual-e5-large under?

multilingual-e5-large is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs multilingual-e5-large well?

With 560M parameters, multilingual-e5-large is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.

What is the best quantization for multilingual-e5-large?

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-large?

multilingual-e5-large 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