Gemma 4 31B
Gemma 4 31B is a multimodal chat model developed by Google, capable of handling text and image inputs and generating text output, with a notable context window of up to 262,144 tokens. It is well-suited for tasks such as text generation, coding, and reasoning, featuring both Dense and Mixture-of-Experts architectures.
Input
Output
Context
262K
Max Output
33K
Parameters
32.7B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters32.7B
Release DateMar 12, 2026
Training CutoffJan 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
22.7%
HLE
62.0%
AA-LCR
85.7%
GPQA
59.9%
Tau2-Bench
75.6%
IFBench
43.4%
SciCode
15.1%
Tau2 Banking
43.4
Coding
29.4
Intelligence
36.4%
Terminal-Bench Hard
43.4%
Terminal-Bench 2.1
35.1
Speed (tok/s)
50.5
TTFA (s)
0.999
TTFT (s)
Estimated GPU Requirements for Gemma 4 31B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Google
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.