Gemma 4 31B
Google馃嚭馃嚫
google/gemma-4-31b-itGemma 4 31B IT is a dense model from Google's open-weight Gemma 4 family that bridges server-grade performance and local execution, ranking near the top of open-model leaderboards. It handles multimodal, hybrid-thinking reasoning across 140+ languages with up to 256K context, well suited for advanced chat, coding, and reasoning.
Cost rate
0.1x
Context
262K
Released
Apr 2, 2026
Input
ImageTextVideo
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Document analysis
#35 路 top 80%
Image understanding
#38 路 top 25%
Mathematical
#46 路 top 12%
Software & IT Services
#60 路 top 15%
Performance
Median latency and throughput measured across recent requests.
Throughput46 tok/s
Latency