File	Format	Size	Description
`functiongemma-thai-toolcall-f16.gguf`	GGUF f16	~525MB	Full precision
`functiongemma-thai-toolcall-Q8_0.gguf`	GGUF Q8_0	~280MB	Recommended ✅
`functiongemma-thai-toolcall-Q4_K_M.gguf`	GGUF Q4_KM	~280MB	Recommended ✅

Usage with Ollama

bash

ollama create functiongemma-thai -f Modelfile
ollama run functiongemma-thai "สวัสดีครับ"

Usage with llama.cpp

./llama-cli -m functiongemma-thai-Q8_0.gguf -n 200 --threads 4 -p "สวัสดีครับ"