---
type: "raw_signal"
id: "google-released-gemma-4-e4b-qat-q4-0-058bf5"
slug: "google-released-gemma-4-e4b-qat-q4-0-058bf5"
title: "Google released Gemma 4 E4B QAT Q4_0 GGUF , a 5.15 GB on-device multimodal model."
description: "Google’s Hugging Face model card lists an instruction-tuned Gemma 4 E4B checkpoint using Quantization-Aware Training (QAT) in GGUF Q4_0 format."
retrieval_nugget: "Google’s Hugging Face model card lists an instruction-tuned Gemma 4 E4B checkpoint using Quantization-Aware Training (QAT) in GGUF Q4_0 format."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "Google’s Hugging Face model card lists an instruction-tuned Gemma 4 E4B checkpoint using Quantization-Aware Training (QAT) in GGUF Q4_0 format. The listed file size is 5.15 GB. Google says QAT is intended to reduce memory requirements while preserving quality similar to bfloat16. The card describes E4B as accepting text, image, and audio input, with a 128K-token context window. This is a ready-to-"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "huggingface.co"
topics: ["google"]
entities: ["Google","Google DeepMind","Gemma 4 E4B","GGUF"]
related_patterns: []
source_url: "https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf"
source_urls: ["https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:google-released-gemma-4-e4b-qat-q4-0-058bf5"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/google-released-gemma-4-e4b-qat-q4-0-058bf5/","markdown":"https://newruntime.com/signals/google-released-gemma-4-e4b-qat-q4-0-058bf5.md","json":"https://newruntime.com/signals/google-released-gemma-4-e4b-qat-q4-0-058bf5.json"}
---

# Google released Gemma 4 E4B QAT Q4_0 GGUF , a 5.15 GB on-device multimodal model.

## Retrieval answer

Google’s Hugging Face model card lists an instruction-tuned Gemma 4 E4B checkpoint using Quantization-Aware Training (QAT) in GGUF Q4_0 format.

Google’s Hugging Face model card lists an instruction-tuned Gemma 4 E4B checkpoint using Quantization-Aware Training (QAT) in GGUF Q4_0 format. The listed file size is 5.15 GB. Google says QAT is intended to reduce memory requirements while preserving quality similar to bfloat16. The card describes E4B as accepting text, image, and audio input, with a 128K-token context window. This is a ready-to-deploy GGUF distribution; the card does not establish device-specific performance or independent quality results for this checkpoint.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)