---
license: mit
language: [en, de, fr, es, zh, ja, ko, ar, hi, pt, ru, it, nl, pl, tr, vi, th, id, sv, da, no, fi, cs, ro, hu, bg, uk, ca, el, hr, sk, sl, et, lt, lv, ms, tl, sw, af, cy, ga, sq, mk, bs, mt, gl, eu, is, ka, hy, kk, uz, az, be, mn, ne, si, km, my, lo, am, ps, sd, ku, ug, bo, dz, fy]
tags: [embeddings, gguf, ggml, text-embeddings, bert, crispembed, ollama]
pipeline_tag: feature-extraction
base_model: intfloat/multilingual-e5-small
---

# multilingual-e5-small GGUF

GGUF format of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) and [Ollama](https://ollama.com).

## Files

| File | Quantization | Size |
|------|-------------|------|
| [multilingual-e5-small-q4_k.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small-q4_k.gguf) | Q4_K | 0 MB |
| [multilingual-e5-small-q8_0.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small-q8_0.gguf) | Q8_0 | 0 MB |
| [multilingual-e5-small.gguf](https://huggingface.co/cstr/multilingual-e5-small-GGUF/resolve/main/multilingual-e5-small.gguf) | F32 | 0 MB |

**Recommended:** Q8_0 for quality (cos vs HF: 0.9999), Q4_K for size (0.990).

## Quick Start

### CrispEmbed
```bash
./crispembed -m multilingual-e5-small "Hello world"
./crispembed-server -m multilingual-e5-small --port 8080
```

### Ollama (with [CrispStrobe fork](https://github.com/CrispStrobe/ollama/tree/feat/xlmr-embedding))
```bash
# Create model
echo "FROM multilingual-e5-small-q8_0.gguf" > Modelfile
ollama create multilingual-e5-small -f Modelfile

# Embed
curl http://localhost:11434/api/embed -d '{"model":"multilingual-e5-small","input":["Hello world"]}'
```

### Python (CrispEmbed)
```python
from crispembed import CrispEmbed
model = CrispEmbed("multilingual-e5-small-q8_0.gguf")
vectors = model.encode(["Hello world", "Goodbye world"])
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | BERT |
| Parameters | 118M |
| Embedding Dimension | 384 |
| Layers | 12 |
| Pooling | mean |
| Tokenizer | SentencePiece |
| Language | multilingual |
| Q8_0 vs HuggingFace | 0.9999 |
| Q4_K vs HuggingFace | 0.990 |

## Server API

CrispEmbed server supports four API dialects:
- `POST /embed` — native
- `POST /v1/embeddings` — OpenAI-compatible
- `POST /api/embed` — Ollama-compatible
- `POST /api/embeddings` — Ollama legacy

## Credits

- Original model: [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)
- Inference: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (MIT, ggml-based)