Google DeepMind

Gemma 4 E4B

Generally availableOpen weights66K contextReasoning

Summary

Gemma 4 E4B is an open-weight language model from Google DeepMind, released on 2 Apr 2026. It accepts text, images and audio and generates text, with a 66K-token context window and up to 8K output tokens per response.

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

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date2 Apr 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window66K (65,536 tokens) [models.dev]
Max output8K tokens [models.dev]
InputText, images and audio [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]

Gemma 4 E4B API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Gemma 4 E4B?

Gemma 4 E4B has a context window of 65,536 tokens (66K) and can generate up to 8,192 tokens in a single response, according to models.dev.

Is Gemma 4 E4B open source?

Gemma 4 E4B is an open-weight model. Check the license terms before commercial use.

When was Gemma 4 E4B released?

Google DeepMind released Gemma 4 E4B on 2 Apr 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Qwen3.5 9B BaseAlibaba (Qwen)26 Feb 202666K––Open
Qwen3.5 35B-A3B BaseAlibaba (Qwen)24 Feb 202666K––Open
AutoGLM Phone 9B MultilingualZhipu AI (Z.ai)10 Dec 202566K$0.04$0.14Open
Trendyol Asure 12BTrendyol19 Feb 202641K––Open
nemotron-voicechatNVIDIA16 Mar 2026128K––Open
DeepSeek V4 Flash 0423DeepSeek23 Apr 2026131K––Open

Change history

  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B
  • Tool calling changed from no to yes
  • Reasoning mode changed from no to yes
  • Input modalities changed from text to text, image, audio
  • Context window changed from 33K to 66K
  • Context window changed from 66K to 33K
  • Tool calling changed from yes to no
  • Reasoning mode changed from yes to no
  • Input modalities changed from text, image, audio to text
  • Name changed from Gemma 4 E4B to Gemma 4 E4B Instruct (IQ4_XS)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B
  • Tool calling changed from no to yes
  • Reasoning mode changed from no to yes
  • Input modalities changed from text to text, image, audio
  • Context window changed from 33K to 66K
  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B Instruct (MLX 4-bit)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B Instruct (IQ4_XS)
  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B Instruct (MLX 4-bit)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B Instruct (IQ4_XS)
  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B Instruct (MLX 4-bit)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B Instruct (IQ4_XS)
  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B Instruct (MLX 4-bit)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B Instruct (IQ4_XS)
  • Name changed from Gemma 4 E4B Instruct (IQ4_XS) to Gemma 4 E4B Instruct (MLX 4-bit)
  • Name changed from Gemma 4 E4B Instruct (MLX 4-bit) to Gemma 4 E4B Instruct (IQ4_XS)

Sources