gemma-4-E4B-it

Name: gemma-4-E4B-it
Author: google

by google

Efficient 4B multimodal VLM with Per-Layer Embeddings for on-device AI

5.7Mdl/month

4.5B (effective)params

HuggingFace Run it on your own data, free

Identifiers

Model ID

google/gemma-4-E4B-it

Feature URI

mixpeek://image_extractor@v1/google_gemma4_e4b_v1

Overview

Gemma 4 E4B is Google DeepMind's efficient multimodal model that uses Per-Layer Embeddings (PLE) to achieve the representational depth of a larger model while maintaining a compact inference footprint. With 4.5 billion effective parameters, it processes text, images, and audio with a 128K token context window, making it one of the most capable small models available.

On Mixpeek, Gemma 4 E4B powers lightweight multimodal understanding tasks including scene captioning, visual question answering, and document analysis where you need strong accuracy without the compute overhead of larger models.

Architecture

Decoder-only transformer with hybrid attention interleaving local sliding-window and full global attention. Uses Per-Layer Embeddings (PLE) that feed a secondary embedding signal into every decoder layer, enabling 4.5B effective parameters from a 2.3B-active compute footprint. Final layer always uses global attention.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so gemma-4-E4B-it runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The model produces text, so it lands in payload. Give the
          // collection a text vector index and embed that text to make it
          // searchable rather than only filterable.
          payload: { extracted_text: modelOutput, source_key: "archive/2026/asset-00412" },
          vectors: { "multimodal-embedding": embeddingOfModelOutput },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// universal_extractor@v1 runs google/gemini-embedding-2
// (3072-d) over a bucket, with no inference of your own.