MU

multilingual e5 small

MultilingualGGUF by cstrUpdated 2026-08-04
Download on Hugging Face
Parameters118M
Context512
Layers12
Architecturebert
Smallest quant0.1 GB
Quick answer

multilingual e5 small needs about 0.8 GB of memory at Q4_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.1 GB (IQ4_XS) to 0.5 GB.

Multilingual E5 small – lightweight text embedding model

Multilingual E5 small is a 12‑layer BERT‑based model with 384‑dimensional embeddings. It supports 100 languages and is optimized for embedding tasks such as retrieval and semantic similarity. The model is released under the MIT license.

Good at

  • Text embeddings for retrieval
  • Semantic similarity scoring
  • Cross‑lingual matching

Limits

  • No vision support
  • Limited to 512‑token context
  • Requires "query:" or "passage:" prefixes for best performance

Best for

  • Embedding queries for search engines
  • Semantic similarity in multilingual apps
  • Feature extraction for downstream classifiers

Who it’s for. Developers building multilingual search or recommendation systems that need compact embeddings. Researchers needing a small, open‑source multilingual embedding model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.1 GB 0.6 GB
Fits Get file →
Q4_K0.1 GB 0.6 GB
Fits Get file →
Q4_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
—0.5 GB 1.0 GB
Fits Get file →

For 8 GB VRAM, Q4_K (0.12 GB) or IQ4_XS (0.12 GB) are suitable. If memory is tighter, use Q4_K. For maximum accuracy with 13 GB VRAM, choose Q8_0 (0.13 GB).

What GPU do you need for multilingual e5 small?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).

Which multilingual e5 small quant should you choose?

Q4_K (0.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ4_XS at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters118M
Layers12
Trained context512 tokens
KV cache (fp16)18 KB per token

Source

Quantized bycstr
Licensemit
Downloads (HF)5,895
Last updated2026-08-04

Frequently asked questions about multilingual e5 small

How much VRAM does multilingual e5 small need?

About 0.8 GB at Q4_K with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run multilingual e5 small on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of multilingual e5 small GGUF?

It depends on the quant: IQ4_XS is 0.1 GB, Q4_K is 0.1 GB, Q4_K is 0.1 GB, Q8_0 is 0.1 GB, file is 0.5 GB.

What context length does multilingual e5 small support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 512.

Where can I download multilingual e5 small GGUF?

The files are on Hugging Face in the cstr/multilingual-e5-small-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does multilingual e5 small use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, Q4_K or IQ4_XS quantizations use about 0.8 GB memory at 8k context, fitting easily in 8 GB VRAM.

Does this model support image inputs?

No, it is a text‑only embedding model with no vision capabilities.

What license applies to this model?

The model is distributed under the MIT license, allowing free use and modification.

Other GGUFs of multilingual-e5-small

Similar models

Browse all →

More from cstr

All by cstr →

More Multilingual models

All Multilingual →

Other tiny models

All tiny models →