Gemma 3n
Collection
2 items • Updated • 7
How to use ggml-org/gemma-3n-E2B-it-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
# 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 ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
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 ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
docker model run hf.co/ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
How to use ggml-org/gemma-3n-E2B-it-GGUF with Ollama:
ollama run hf.co/ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
How to use ggml-org/gemma-3n-E2B-it-GGUF with Docker Model Runner:
docker model run hf.co/ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
How to use ggml-org/gemma-3n-E2B-it-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ggml-org/gemma-3n-E2B-it-GGUF:Q8_0
lemonade run user.gemma-3n-E2B-it-GGUF-Q8_0
lemonade list
This version does not contain multimodal support. We are still working on adding multimodal.
Original model: https://huggingface.co/google/gemma-3n-E2B-it
Model Page: Gemma 3n
Resources and Technical Documentation:
Terms of Use: Terms
Authors: Google DeepMind
To install llama.cpp on your system, see installation guide
llama-cli -hf ggml-org/gemma-3n-E2B-it-GGUF:Q8_0 -fa -c 0 --jinja
Search for gemma-3n-E2B-it-GGUF and add it to your model library
8-bit
16-bit