by Google
31B open-weight model from Google for local AI inference.
Parameters
31B
RAM Required
24 GB
Context
4,096
Benchmark scores not yet verified for this model.
⇩ 197,759 downloads on HuggingFace
How to Get This Model
Ollama
ollama pull gemma-4-31b-it-qat:31b
HuggingFace
View model page →
LM Studio
Search "gemma-4-31B-it-qat-GGUF" in LM Studio's Discover tab, or download the GGUF above.
