--- title: Drive-Thru Gemma emoji: 🍔 colorFrom: yellow colorTo: red sdk: gradio sdk_version: 5.23.0 app_file: app.py pinned: false suggested_hardware: zero-a10g --- Gemma 4 E2B QAT Q4_0 API (`google/gemma-4-E2B-it-qat-q4_0-gguf`). `POST /gradio_api/call/generate` with `{"data": [system, user, max_new_tokens, temperature]}`. Inference runs the 4-bit GGUF on CPU, so requests do not wait for a ZeroGPU slot.