GGUF

Gemma 3 27B QAT

google

gemma

Google's Gemma 3 27B model in new quantization format that preserves bfloat16 quality

Model info

Model

Gemma 3 27B QAT

Author

google

Arch

gemma

Parameters

27B

Format

gguf

Size on disk

about 16.43 GB

Download and run Gemma 3 27B QAT

Open in LM Studio to view download options

Download gemma-3-27b-it-qat from the terminal

Download the model using lms — LM Studio's developer CLI.

lms get gemma-3-27b-it-qat

Call gemma-3-27b-it-qat from your code

curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-3-27b-it-qat",
    "messages": [
      { "role": "system", "content": "Always answer in rhymes." },
      { "role": "user", "content": "Introduce yourself." }
    ],
    "temperature": 0.7,
    "max_tokens": -1,
    "stream": true
  }'

Next Steps: Build! 🔨

Learn more


lmmy