Instructions to use agiws/gemma4-llama-cpp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use agiws/gemma4-llama-cpp 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 agiws/gemma4-llama-cpp:Q4_K_M # Run inference directly in the terminal: llama cli -hf agiws/gemma4-llama-cpp:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf agiws/gemma4-llama-cpp:Q4_K_M # Run inference directly in the terminal: llama cli -hf agiws/gemma4-llama-cpp:Q4_K_M
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 server with a web UI: ./build/bin/llama serve -hf agiws/gemma4-llama-cpp:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf agiws/gemma4-llama-cpp:Q4_K_M
Use Docker
docker model run hf.co/agiws/gemma4-llama-cpp:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use agiws/gemma4-llama-cpp with Ollama:
ollama run hf.co/agiws/gemma4-llama-cpp:Q4_K_M
- Unsloth Desktop
- Pi
How to use agiws/gemma4-llama-cpp with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf agiws/gemma4-llama-cpp:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "agiws/gemma4-llama-cpp:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use agiws/gemma4-llama-cpp with Docker Model Runner:
docker model run hf.co/agiws/gemma4-llama-cpp:Q4_K_M
- Lemonade
How to use agiws/gemma4-llama-cpp with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull agiws/gemma4-llama-cpp:Q4_K_M
Run and chat with the model
lemonade run user.gemma4-llama-cpp-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use agiws/gemma4-llama-cpp with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf agiws/gemma4-llama-cpp:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default agiws/gemma4-llama-cpp:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use agiws/gemma4-llama-cpp with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf agiws/gemma4-llama-cpp:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "agiws/gemma4-llama-cpp:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
|
Download README.md from agiws/gemma4-llama-cpp: direct link, hf CLI and curl.
- Browser
- Download file 1.83 kB
-
https://huggingface.co/agiws/gemma4-llama-cpp/resolve/main/README.md
- Command line
-
hf download hf://agiws/gemma4-llama-cpp/README.md
-
curl -L -o README.md https://huggingface.co/agiws/gemma4-llama-cpp/resolve/main/README.md
1.83 kB
| # llama.cpp (fork) β Gemma 4 + audio (mtmd) | |
| Source snapshot of the private llama.cpp fork used by AGIWS inference workers. | |
| ## What is inside | |
| - `src/models/gemma4.cpp`, `gemma4-assistant.cpp` β text models `gemma4`, `gemma4-assistant`. | |
| - `tools/mtmd/clip.cpp` β graphs `clip_graph_gemma4a` / `clip_graph_gemma4ua` (audio encoders). | |
| - `tools/mtmd/mtmd-audio.cpp` β preprocessors `gemma4a` / `gemma4ua`, mel filters, streaming. | |
| - `tools/mtmd/mtmd.h` β `mtmd_support_audio`, `mtmd_bitmap_init_from_audio`. | |
| - `tools/server` β OpenAI-compatible server accepting `input_audio` content parts. | |
| - `conversion/gemma.py` β `Gemma4Model` GGUF converter (`Gemma4ForConditionalGeneration`). | |
| ## Files | |
| - `src/llama-cpp-src.tar.gz` β full source tree (no `.git`, no build artifacts). | |
| - `lib/*.so` β prebuilt CUDA libraries and `llama-server` for T4 (sm_75), uploaded by the build job. | |
| - `lib/BUILD_INFO.txt` β compiler, CUDA version, git-less snapshot hash, sha256 of every artifact. | |
| ## Build (Colab T4) | |
| ```bash | |
| tar -xzf src/llama-cpp-src.tar.gz -C /content/llama-cpp-fork | |
| cmake -S /content/llama-cpp-fork -B /content/llama-cpp-fork/build \ | |
| -DCMAKE_BUILD_TYPE=Release \ | |
| -DGGML_CUDA=ON \ | |
| -DGGML_NATIVE=OFF \ | |
| -DCMAKE_CUDA_ARCHITECTURES=75 \ | |
| -DBUILD_SHARED_LIBS=ON \ | |
| -DLLAMA_CURL=OFF \ | |
| -DLLAMA_BUILD_TESTS=OFF \ | |
| -DLLAMA_BUILD_EXAMPLES=OFF | |
| cmake --build /content/llama-cpp-fork/build -j"$(nproc)" --target llama-server | |
| ``` | |
| Artifacts needed at runtime: `llama-server` plus `libllama.so*`, `libmtmd.so*`, `libggml*.so*` | |
| (`libggml-base`, `libggml-cpu`, `libggml-cuda`, `libggml`). | |
| Runtime flags for Gemma audio: | |
| ```bash | |
| LD_LIBRARY_PATH=/content/llama/lib \ | |
| /content/llama/lib/llama-server -m .../gemma-4-12b-it-Q4_K_M.gguf \ | |
| --mmproj .../mmproj-F16.gguf -ngl 99 -c 4096 --host 127.0.0.1 --port 8091 | |
| ``` | |