Gemma 4 31B
A dense Gemma 4 model for text and image understanding at a larger scale.
- Published size
- ~31B
- Active parameters
- ~31B
- Context window
- 256K
- Architecture
- Dense · vision
- License
- Apache 2.0
Deployment considerations
Use it as a dense counterpart to Gemma 4 26B-A4B. Quantization, context length, and image inputs each affect the memory budget.
The card lists 30.7B language-model parameters with an approximately 550M-parameter vision encoder; 31B is the rounded model name.
GPU memory estimates and minimum / recommended configurations are pending. This profile does not contain measured deployment results.
GPU requirements
- Minimum
- —GPU / VRAM · pending
- Recommended
- —GPU / VRAM · pending
Memory estimates and tested configurations will appear here after checkpoint review and deployment testing.
No invented leaderboards.
Latency, throughput, and cost per token will appear here after a reproducible run. Until then, this page helps you understand the model—not predict its performance.
Gemma 4 31B deployment FAQ
How much GPU memory does Gemma 4 31B need?
The full checkpoint weight footprint is pending review. Minimum and recommended GPU configurations will be added after testing; the model name or active parameter count alone is not a memory requirement.
Has BenchGrid benchmarked Gemma 4 31B?
Not yet. This profile contains publisher specifications and calculated weight-memory estimates. We do not currently publish measured latency, throughput, or cost per token for this model.
Where do these specifications come from?
The specifications are based on the official Google model card linked on this page. Memory estimates use the stated total parameter count, including inactive experts for MoE models. Nominal model sizes are labeled with ~.
Explore your compute options.
Check available hardware, quotas, and current pricing with the provider. These links are not verified deployments or performance recommendations.
