CoolFace
Apppublic

chmielvu/gemma-3-270m-heretic

sourceHugging Facegemmaupdated 6mo agoView on Hugging Face
0likes
App README

Gemma 3 270M Instruct (Q4KS)

Gemma 3 270M Instruct - Compact instruction-following model from Google, quantized by Unsloth.

API Endpoints

  • —POST /v1/chat/completions - OpenAI-compatible chat completions (supports streaming)
  • —GET /v1/models - List available models
  • —GET /health - Health check

Usage

bash
curl -X POST "https://YOUR_SPACE.hf.space/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}]}'

Tech

  • —llama.cpp via JamePeng fork (Luigi wheel v0.3.22)
  • —chat_format: gemma
  • —Model: unsloth/gemma-3-270m-it-GGUF (Q4KS)