← Back to models

Gemma 4 E2B QAT

generatorAnswers

Generate answers, summaries, and text with the smallest instruction-tuned Gemma 4 checkpoint. Quantization-aware training prepares it for Q4_0 weights.

antfly inference pull google/gemma-4-E2B-it-qat-q4_0-gguf:gguf
By googleLicense: apache-2.0Hugging Face source

Technical Specs

Architecture
Gemma 4 E2B
QATQ4_0GGUF

Usage

Pull the model

antfly inference pull google/gemma-4-E2B-it-qat-q4_0-gguf:gguf

Start Antfly Inference

# With Antfly standalone (Antfly Inference enabled by default)
antfly standalone

# Or run Antfly Inference on its own, listening on 127.0.0.1:8090
antfly inference run

Use in configuration

{
  "generators": {
    "local": {
      "provider": "antfly",
      "model": "google/gemma-4-E2B-it-qat-q4_0-gguf:gguf"
    }
  }
}