Gemma 4 E2B IT

Tool callingStructured outputReasoningImage inputAudio input

Model card Launch post Website Docs

Open Gemma instruction model for efficient chat and self-hosted deployments

Context: 131K
Released: 6mo ago
Parameters: —

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Google DeepMind
Model family: Gemma
Type: Language model
Predecessor: —
Successor: —
Released: April 2, 2026
Model ID: google/gemma-4-E2B-it
Openness: Open weights
License: —
Parameters: —
Input modalities: text, image, audio
Output modalities: text
Modality: text+image+audio->text
Max output tokens: 8K
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: google/gemma-4-E2B-it
Source family: gemma
Last updated: 2026-04-02
Model context: 131K
Model output limit: 8K
Open weights: Yes
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Complete source record (JSON)

{
  "id": "google/gemma-4-E2B-it",
  "name": "Gemma 4 E2B IT",
  "description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
  "family": "gemma",
  "last_updated": "2026-04-02",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "audio"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 8192
  },
  "release_date": "2026-04-02",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/google/gemma-4-E2B-it"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider endpoint data will appear after this model's first OpenRouter endpoint sync.

Text provenance

Gemini app/web

Google SynthID text watermarking

Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.

Official explanation

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware