All AI models · LLM benchmarks · Methodology

Google

Gemma 4 E4B Instruct

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

Model facts

Context window
33K tokens
Maximum output
8K tokens
Cheapest paid input
$0.04 per 1M tokens
Cheapest paid output
$0.2 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

tool calling, structured output, attachments, temperature control, open weights, text, image, audio, video.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning12.29.4not measured34.1
Non-reasoning8.7not measurednot measured44.2

Observed price history

  • 2026-08-24: $0.04 input / $0.2 output per 1M tokens

API providers

  • Atomic Chat (IQ4_XS) — model id gemma-4-E4B-it-IQ4_XS; free input / free output per 1M tokens; provider documentation
  • Atomic Chat (MLX 4-bit) — model id gemma-4-E4B-it-MLX-4bit; free input / free output per 1M tokens; provider documentation
  • NanoGPT — model id gemma-4-e4b-it; $0.04 input / $0.2 output per 1M tokens; provider documentation