About Gemma 4 31B
Gemma 4 31B is the largest dense multimodal model in the Gemma 4 family with 31 billion parameters. It supports text, image, and video inputs with a 256K token context window and over 140 languages.
It is the largest Gemma 4 variant. Gemma 4 introduces Per-Layer Embeddings (PLE) for richer token representations, shared KV cache for efficient long-context inference, and variable aspect ratio vision encoding.
| Metric | Value |
|---|---|
| Parameter Count | 31 billion |
| Mixture of Experts | No |
| Context Length | 256,000 tokens |
| Multilingual | Yes (140+ langs) |
| Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with Gemma 4 31B?
Try Gemma 4 31B in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "gemma-4-31b-it",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'