Gemma 4 31B IT

Google · Gemma 4
LLMApache-2.0publicTrusted31B params

Gemma 4 31B, instruction-tuned: Google's largest dense open model, chat with images.

Gemma 4 31B, instruction-tuned: Google's largest dense open model, chat with images.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 31B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 69 GB+ VRAM
  • dtype: Bf16, Fp16