Typhoon2.1 Gemma3 4b Gguf

🚀 Typhoon2.1-Gemma3-4B

Typhoon2.1-Gemma3-4B is a Thai instruct large language model. It has 4 billion parameters, a 128K context length, and function - calling capabilities. Based on Gemma3 4B, this model offers strong text - generation capabilities.

📄 License

The model uses the gemma license.

📦 Installation

Install llama.cpp

You can install llama.cpp through brew (works on Mac and Linux):

brew install llama.cpp

💻 Usage Examples

CLI Usage

llama-cli --hf-repo scb10x/typhoon2.1-gemma3-4b-gguf --hf-file typhoon2.1-gemma3-4b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server Usage

llama-server --hf-repo scb10x/typhoon2.1-gemma3-4b-gguf --hf-file typhoon2.1-gemma3-4b-q4_k_m.gguf -c 2048

Another Usage Method

You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo. Here are the detailed steps:

Step 1: Clone llama.cpp from GitHub

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

Step 2: Build llama.cpp

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

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run Inference

./llama-cli --hf-repo scb10x/typhoon2.1-gemma3-4b-gguf --hf-file typhoon2.1-gemma3-4b-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo scb10x/typhoon2.1-gemma3-4b-gguf --hf-file typhoon2.1-gemma3-4b-q4_k_m.gguf -c 2048

📚 Documentation

Model Information

Performance

⚠️ Important Note

This is a text - only model.