---
base_model:
- google/gemma-4-E4B-it
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- llama-cpp
- moe
- e4b
---

# **gemma-4-E4B-it-GGUF**

> Gemma-4-E4B-it from Google is a 4.5B effective parameter (8B total with Per-Layer Embeddings) multimodal dense model in the Gemma 4 family, optimized for edge deployment on laptops, high-end smartphones, and consumer GPUs with native support for text, images (variable aspect ratio/resolution), audio processing, and configurable thinking modes for step-by-step reasoning. Featuring 42 layers, 512-token sliding window, 128K context length, and 262K vocabulary, it delivers frontier-level performance in agentic workflows, multilingual OCR/handwriting recognition, document/PDF parsing, UI/screen analysis, chart interpretation, object detection with pointing, coding assistance, and low-latency speech-to-text understanding—rivaling models 10-20x larger while maintaining Google's production-grade safety alignments. The instruction-tuned variant excels at on-device autonomous agents via Android AICore/Qualcomm optimizations, with open weights enabling local-first inference (MediaTek/ARM CPUs, NVIDIA RTX) for privacy-focused applications like mobile IDEs, real-time document processing, and structured data extraction in resource-constrained environments.

## Model Files

   File Name | Quant Type | File Size | File Link |
 |-----------|------------|-----------|-----------|
 | gemma-4-E4B-it.BF16.gguf | BF16 | 15.1 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.BF16.gguf) |
 | gemma-4-E4B-it.F16.gguf | F16 | 15.1 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.F16.gguf) |
 | gemma-4-E4B-it.Q2_K.gguf | Q2_K | 4.4 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q2_K.gguf) |
 | gemma-4-E4B-it.Q3_K_L.gguf | Q3_K_L | 5.02 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q3_K_L.gguf) |
 | gemma-4-E4B-it.Q3_K_M.gguf | Q3_K_M | 4.85 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q3_K_M.gguf) |
 | gemma-4-E4B-it.Q3_K_S.gguf | Q3_K_S | 4.65 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q3_K_S.gguf) |
 | gemma-4-E4B-it.Q4_0.gguf | Q4_0 | 5.19 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q4_0.gguf) |
 | gemma-4-E4B-it.Q4_K_M.gguf | Q4_K_M | 5.34 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q4_K_M.gguf) |
 | gemma-4-E4B-it.Q4_K_S.gguf | Q4_K_S | 5.2 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q4_K_S.gguf) |
 | gemma-4-E4B-it.Q5_0.gguf | Q5_0 | 5.69 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q5_0.gguf) |
 | gemma-4-E4B-it.Q5_K_M.gguf | Q5_K_M | 5.76 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q5_K_M.gguf) |
 | gemma-4-E4B-it.Q5_K_S.gguf | Q5_K_S | 5.69 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q5_K_S.gguf) |
 | gemma-4-E4B-it.Q6_K.gguf | Q6_K | 6.22 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q6_K.gguf) |
 | gemma-4-E4B-it.Q8_0.gguf | Q8_0 | 8.01 GB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.Q8_0.gguf) |
 | gemma-4-E4B-it.mmproj-bf16.gguf | mmproj-bf16 | 992 MB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.mmproj-bf16.gguf) |
 | gemma-4-E4B-it.mmproj-f16.gguf | mmproj-f16 | 992 MB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.mmproj-f16.gguf) |
 | gemma-4-E4B-it.mmproj-q8_0.gguf | mmproj-q8_0 | 560 MB | [Download](https://huggingface.co/prithivMLmods/gemma-4-E4B-it-GGUF/blob/main/gemma-4-E4B-it.mmproj-q8_0.gguf) |

## llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp