Instructions to use TwinSunsLLC/multilingual-e5-small-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TwinSunsLLC/multilingual-e5-small-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf TwinSunsLLC/multilingual-e5-small-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf TwinSunsLLC/multilingual-e5-small-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 TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf TwinSunsLLC/multilingual-e5-small-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 TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TwinSunsLLC/multilingual-e5-small-gguf:Q8_0

Use Docker

docker model run hf.co/TwinSunsLLC/multilingual-e5-small-gguf:Q8_0

LM Studio
Jan
Ollama
How to use TwinSunsLLC/multilingual-e5-small-gguf with Ollama:
```
ollama run hf.co/TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
```

Unsloth Studio

How to use TwinSunsLLC/multilingual-e5-small-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 TwinSunsLLC/multilingual-e5-small-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 TwinSunsLLC/multilingual-e5-small-gguf to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use TwinSunsLLC/multilingual-e5-small-gguf with Docker Model Runner:
```
docker model run hf.co/TwinSunsLLC/multilingual-e5-small-gguf:Q8_0
```

Lemonade

How to use TwinSunsLLC/multilingual-e5-small-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TwinSunsLLC/multilingual-e5-small-gguf:Q8_0

Run and chat with the model

lemonade run user.multilingual-e5-small-gguf-Q8_0

List all available models

lemonade list

Atomic Chat

multilingual-e5-small — GGUF (Q8_0)

GGUF conversion of intfloat/multilingual-e5-small, quantized to Q8_0, for on-device retrieval in Offline AI: Private Chat.

384 dimensions, 12 layers, 512 max tokens
126 MB (f16 is 236 MB)
Runs via llama.cpp / llama.swift with embeddings = true and mean pooling

Quantization is free here

Q8_0 matches f16 to three decimal places on cosine similarity, and produces an identical ranking order — which is what retrieval actually depends on.

Pair	Q8_0	f16
EN paraphrase	0.868	0.868
EN → FR translation	0.896	0.896
EN → ES translation	0.843	0.843
query → correct passage	0.848	0.848
EN → unrelated topic	0.737	0.736
query → wrong passage	0.671	0.671

Note the high floor: unrelated text still scores 0.737. Rank by top-k; do not use an absolute similarity threshold.

Usage

E5 is asymmetric — prefix stored text with passage: and queries with query: . Omitting the prefixes degrades retrieval, and mixing them is worse than using neither.

Conversion

convert_hf_to_gguf.py fails on this model with BPE pre-tokenizer was not recognized: it declares architectures: ["BertModel"] but ships an XLM-RoBERTa SentencePiece tokenizer. Rewrite config.json to architectures: ["XLMRobertaModel"] first, then convert and quantize.

License

MIT, inherited from the base model. Copyright belongs to the original authors — see intfloat/multilingual-e5-small.

Downloads last month: 105

GGUF

Model size

0.1B params

Architecture

bert

Hardware compatibility

8-bit

Model tree for TwinSunsLLC/multilingual-e5-small-gguf

Base model

intfloat/multilingual-e5-small

Quantized

(269)

this model