prithivMLmods/gemma-4-E2B-it-GGUF overview
gemma 4 E2B it GGUF Gemma 4 E2B it from Google is an ultra efficient 2.3B effective parameter 5.1B total with Per Layer Embeddings multimodal dense model in th…
Runs locally from ~531.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma-4-E2B-it.BF16.gguf | GGUF | GGUF | 8.67 GB | Download |
| gemma-4-E2B-it.F16.gguf | GGUF | GGUF | 8.67 GB | Download |
| gemma-4-E2B-it.Q2_K.gguf | GGUF | GGUF | 2.78 GB | Download |
| gemma-4-E2B-it.Q3_K_L.gguf | GGUF | GGUF | 3.06 GB | Download |
| gemma-4-E2B-it.Q3_K_M.gguf | GGUF | GGUF | 2.98 GB | Download |
| gemma-4-E2B-it.Q3_K_S.gguf | GGUF | GGUF | 2.90 GB | Download |
| gemma-4-E2B-it.Q4_0.gguf | GGUF | GGUF | 3.13 GB | Download |
| gemma-4-E2B-it.Q4_K_M.gguf | GGUF | GGUF | 3.19 GB | Download |
| gemma-4-E2B-it.Q4_K_S.gguf | GGUF | GGUF | 3.13 GB | Download |
| gemma-4-E2B-it.Q5_0.gguf | GGUF | GGUF | 3.35 GB | Download |
| gemma-4-E2B-it.Q5_K_M.gguf | GGUF | GGUF | 3.38 GB | Download |
| gemma-4-E2B-it.Q5_K_S.gguf | GGUF | GGUF | 3.35 GB | Download |
| gemma-4-E2B-it.Q6_K.gguf | GGUF | GGUF | 3.58 GB | Download |
| gemma-4-E2B-it.Q8_0.gguf | GGUF | GGUF | 4.61 GB | Download |
| gemma-4-E2B-it.mmproj-bf16.gguf | GGUF | BF16 | 941.1 MB | Download |
| gemma-4-E2B-it.mmproj-f16.gguf | GGUF | F16 | 941.1 MB | Download |
| gemma-4-E2B-it.mmproj-q8_0.gguf | GGUF | Q8_0 | 531.5 MB | Download |
Model Details
| Model ID | prithivMLmods/gemma-4-E2B-it-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | google/gemma-4-E2B-it |
| Last modified | 2026-06-07T04:54:13.000Z |
Model README
---
license: apache-2.0
language:
- en
base_model:
- google/gemma-4-E2B-it
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- llama-cpp
- moe
- e2b
---
gemma-4-E2B-it-GGUF
> Gemma-4-E2B-it from Google is an ultra-efficient 2.3B effective parameter (5.1B total with Per-Layer Embeddings) multimodal dense model in the Gemma 4 family, purpose-built for on-device deployment across smartphones, laptops, Raspberry Pi, and IoT edge hardware with native support for text, images (variable aspect ratio/resolution), audio, and configurable thinking modes for advanced reasoning. Featuring 35 layers, 512-token sliding window, 128K context length, and 262K vocabulary, it excels at agentic workflows, OCR (multilingual/handwriting), document/PDF parsing, UI/screen understanding, chart comprehension, object detection, coding assistance, and low-latency inference optimized for Qualcomm/MediaTek chips via Android AICore—delivering frontier-level intelligence rivaling models 20x larger while consuming minimal RAM/battery. The instruction-tuned variant prioritizes seamless integration for mobile developers prototyping autonomous agents, with safety protocols matching Google's proprietary standards and open weights enabling local-first AI servers on consumer GPUs for reasoning-heavy tasks like IDE assistance and structured data extraction.
Model Files
File Name | Quant Type | File Size | File Link |
|-----------|------------|-----------|-----------|
| gemma-4-E2B-it.BF16.gguf | BF16 | 9.31 GB | Download |
| gemma-4-E2B-it.F16.gguf | F16 | 9.31 GB | Download |
| gemma-4-E2B-it.Q2_K.gguf | Q2_K | 2.99 GB | Download |
| gemma-4-E2B-it.Q3_K_L.gguf | Q3_K_L | 3.28 GB | Download |
| gemma-4-E2B-it.Q3_K_M.gguf | Q3_K_M | 3.2 GB | Download |
| gemma-4-E2B-it.Q3_K_S.gguf | Q3_K_S | 3.11 GB | Download |
| gemma-4-E2B-it.Q4_0.gguf | Q4_0 | 3.36 GB | Download |
| gemma-4-E2B-it.Q4_K_M.gguf | Q4_K_M | 3.43 GB | Download |
| gemma-4-E2B-it.Q4_K_S.gguf | Q4_K_S | 3.37 GB | Download |
| gemma-4-E2B-it.Q5_0.gguf | Q5_0 | 3.6 GB | Download |
| gemma-4-E2B-it.Q5_K_M.gguf | Q5_K_M | 3.63 GB | Download |
| gemma-4-E2B-it.Q5_K_S.gguf | Q5_K_S | 3.6 GB | Download |
| gemma-4-E2B-it.Q6_K.gguf | Q6_K | 3.85 GB | Download |
| gemma-4-E2B-it.Q8_0.gguf | Q8_0 | 4.95 GB | Download |
| gemma-4-E2B-it.mmproj-bf16.gguf | mmproj-bf16 | 987 MB | Download |
| gemma-4-E2B-it.mmproj-f16.gguf | mmproj-f16 | 987 MB | Download |
| gemma-4-E2B-it.mmproj-q8_0.gguf | mmproj-q8_0 | 557 MB | Download |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/gemma-4-E2B-it-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models