---

license: gemma pipeline_tag: sentence-similarity library_name: sentence-transformers tags:

• sentence-transformers
• sentence-similarity
• feature-extraction
• text-embeddings-inference
• llama-cpp
• gguf-my-repo

extragatedheading: Access EmbeddingGemma on Hugging Face extragatedprompt: To access EmbeddingGemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging Face and click below. Requests are processed immediately. extragatedbutton_content: Acknowledge license base_model: google/embeddinggemma-300m

---

admiralakber/embeddinggemma-300m-Q4KM-GGUF

This model was converted to GGUF format from google/embeddinggemma-300m using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo admiralakber/embeddinggemma-300m-Q4KM-GGUF --hf-file embeddinggemma-300m-q4km.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo admiralakber/embeddinggemma-300m-Q4KM-GGUF --hf-file embeddinggemma-300m-q4km.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMACURL=1 flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo admiralakber/embeddinggemma-300m-Q4KM-GGUF --hf-file embeddinggemma-300m-q4km.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo admiralakber/embeddinggemma-300m-Q4KM-GGUF --hf-file embeddinggemma-300m-q4km.gguf -c 2048