How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible embeddings server:
llama serve -hf ggml-org-dev/bert-bge-small-GGUF:F16 --embeddings
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible embeddings server:
llama serve -hf ggml-org-dev/bert-bge-small-GGUF:F16 --embeddings
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible embeddings server:
./build/bin/llama serve -hf ggml-org-dev/bert-bge-small-GGUF:F16 --embeddings
Quick Links

bert-bge-small-GGUF

Tiny model used by the llama.cpp test suite and CI. It is not meant for real-world use.

Originally hosted at ggml-org/models/bert-bge-small/.

F16 conversion of BAAI/bge-small-en-v1.5 for embedding tests, plus a big-endian variant.

Downloads last month
4,761
GGUF
Model size
33.2M params
Architecture
bert
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support