Instructions to use Lorelum/granite-embedding-97m-multilingual-r2-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 Lorelum/granite-embedding-97m-multilingual-r2-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 Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_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 Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_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 Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0

Use Docker

docker model run hf.co/Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use Lorelum/granite-embedding-97m-multilingual-r2-GGUF with Ollama:
```
ollama run hf.co/Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
```
Unsloth Desktop
Docker Model Runner
How to use Lorelum/granite-embedding-97m-multilingual-r2-GGUF with Docker Model Runner:
```
docker model run hf.co/Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0
```

Lemonade

How to use Lorelum/granite-embedding-97m-multilingual-r2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lorelum/granite-embedding-97m-multilingual-r2-GGUF:Q4_0

Run and chat with the model

lemonade run user.granite-embedding-97m-multilingual-r2-GGUF-Q4_0

List all available models

lemonade list

Atomic Chat

Granite Embedding 97M Multilingual R2 — Q4_0 GGUF

Q4_0 quantization of IBM Granite Embedding 97M Multilingual R2, prepared for Lorelum's local CPU embedding service. This is a derivative artifact maintained by Lorelum, not an official IBM release.

File

Filename: granite-q4_0.gguf
Size: 66,345,216 bytes
SHA-256: 18e8ce8ce834790618e90d26bed465cca87362076f3042eb0d8eee0732596f59
Embedding dimensions: 384
Lorelum uses CLS pooling and L2 normalization, with no query or document prefix.

Provenance and quantization

Original model: ibm-granite/granite-embedding-97m-multilingual-r2.

F16 GGUF conversion by ATF:

Source file: granite-embedding-97m-multilingual-r2-f16.gguf
Source size: 206,403,072 bytes
Source SHA-256: 74075aeea7bd9ac4e5d74755e216fa487f5b6cce9ac6c5a363936370585b1a38

Quantized from that F16 file, without requantization, using llama.cpp b10901, commit 28ff0958291ce3465fabd7bd679d4b0edd742bd9:

llama-quantize --pure --token-embedding-type q4_0 \
  granite-embedding-97m-multilingual-r2-f16.gguf \
  granite-q4_0.gguf Q4_0 4

Matrix weights and the token embedding table use Q4_0; normalization vectors remain F32. This is the pure Q4_0 artifact, not Q4_K_M.

Usage

Download with the Hugging Face CLI:

hf download Lorelum/granite-embedding-97m-multilingual-r2-GGUF \
  granite-q4_0.gguf --local-dir ./models

Load it with a compatible llama.cpp embedding runtime. Lorelum validates the artifact size and SHA-256 before loading it. This artifact was tested with CPU inference on macOS arm64; publication alone does not establish compatibility or performance on other hardware.

License and attribution

The original IBM model and ATF conversion declare Apache-2.0. This repository includes the Apache-2.0 LICENSE, the upstream model card, and the source GGUF model card to retain source documentation and attribution. The modification made here is Q4_0 quantization; no additional training was performed.

Downloads last month: 229

GGUF

Model size

97.4M params

Architecture

modern-bert

Hardware compatibility

4-bit

Model tree for Lorelum/granite-embedding-97m-multilingual-r2-GGUF

Base model

ibm-granite/granite-embedding-97m-multilingual-r2

Quantized

(18)

this model