Instructions to use cstr/multilingual-e5-base-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/multilingual-e5-base-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cstr/multilingual-e5-base-GGUF",
	filename="multilingual-e5-base-q4_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cstr/multilingual-e5-base-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/multilingual-e5-base-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/multilingual-e5-base-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cstr/multilingual-e5-base-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cstr/multilingual-e5-base-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf cstr/multilingual-e5-base-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf cstr/multilingual-e5-base-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf cstr/multilingual-e5-base-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/multilingual-e5-base-GGUF:Q8_0

Use Docker

docker model run hf.co/cstr/multilingual-e5-base-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use cstr/multilingual-e5-base-GGUF with Ollama:
```
ollama run hf.co/cstr/multilingual-e5-base-GGUF:Q8_0
```

Unsloth Studio new

How to use cstr/multilingual-e5-base-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cstr/multilingual-e5-base-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cstr/multilingual-e5-base-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/multilingual-e5-base-GGUF to start chatting

Docker Model Runner
How to use cstr/multilingual-e5-base-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/multilingual-e5-base-GGUF:Q8_0
```

Lemonade

How to use cstr/multilingual-e5-base-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/multilingual-e5-base-GGUF:Q8_0

Run and chat with the model

lemonade run user.multilingual-e5-base-GGUF-Q8_0

List all available models

lemonade list

multilingual-e5-base-GGUF / README.md

cstr

Add model card for multilingual-e5-base GGUF

f706712 verified about 1 month ago

preview code

raw

history blame contribute delete

2.61 kB

	---
	license: mit
	language: [multilingual]
	tags: [embeddings, gguf, ggml, text-embeddings, xlm-r, crispembed]
	pipeline_tag: feature-extraction
	base_model: intfloat/multilingual-e5-base
	---

	# multilingual-e5-base GGUF

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

	Multilingual E5 Base. 100+ languages, 768-dimensional mean-pooled. Use prefix: "query: " / "passage: ".

	## Files

	\| File \| Quantization \| Size \|
	\|------\|-------------\|------\|
	\| [multilingual-e5-base-q4_k.gguf](https://huggingface.co/cstr/multilingual-e5-base-GGUF/resolve/main/multilingual-e5-base-q4_k.gguf) \| Q4_K \| 247 MB \|
	\| [multilingual-e5-base-q8_0.gguf](https://huggingface.co/cstr/multilingual-e5-base-GGUF/resolve/main/multilingual-e5-base-q8_0.gguf) \| Q8_0 \| 287 MB \|
	\| [multilingual-e5-base.gguf](https://huggingface.co/cstr/multilingual-e5-base-GGUF/resolve/main/multilingual-e5-base.gguf) \| F32 \| 1066 MB \|


	## Quick Start

	```bash
	# Download
	huggingface-cli download cstr/multilingual-e5-base-GGUF multilingual-e5-base-q4_k.gguf --local-dir .

	# Run with CrispEmbed
	./crispembed -m multilingual-e5-base-q4_k.gguf "Hello world"

	# Or with auto-download
	./crispembed -m multilingual-e5-base "Hello world"
	```

	## Model Details

	\| Property \| Value \|
	\|----------\|-------\|
	\| Architecture \| XLM-R \|
	\| Parameters \| 278M \|
	\| Embedding Dimension \| 768 \|
	\| Layers \| 12 \|
	\| Pooling \| mean \|
	\| Tokenizer \| SentencePiece \|
	\| Base Model \| [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) \|

	## Verification

	Verified bit-identical to HuggingFace sentence-transformers (cosine similarity >= 0.999 on test texts).

	## Usage with CrispEmbed

	CrispEmbed is a lightweight C/C++ text embedding inference engine using ggml.
	No Python runtime, no ONNX. Supports BERT, XLM-R, Qwen3, and Gemma3 architectures.

	```bash
	# Build CrispEmbed
	git clone https://github.com/CrispStrobe/CrispEmbed
	cd CrispEmbed
	cmake -S . -B build && cmake --build build -j

	# Encode
	./build/crispembed -m multilingual-e5-base-q4_k.gguf "query text"

	# Server mode
	./build/crispembed-server -m multilingual-e5-base-q4_k.gguf --port 8080
	curl -X POST http://localhost:8080/v1/embeddings \
	-d '{"input": ["Hello world"], "model": "multilingual-e5-base"}'
	```

	## Credits

	- Original model: [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base)
	- Inference engine: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (ggml-based)
	- Conversion: `convert-bert-embed-to-gguf.py`