About Gemma 4 E2B
Gemma 4 E2B is a lightweight multimodal model with 2.3 billion effective parameters (5.1B with embeddings). It supports text, image, video, and audio inputs with a 128K token context window and over 140 languages.
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. Despite its small size, it delivers strong performance across multimodal understanding tasks.
| Metric | Value |
|---|---|
| Parameter Count | 2.3B effective |
| Mixture of Experts | No |
| Context Length | 128,000 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 E2B?
Try Gemma 4 E2B 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-e2b-it",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'