Model Intelligence Sheet
tinku1102/gemma-magazine-2b-mobile-gguf overview
license: apache 2.0 base model: google/gemma 2 2b it tags: gemma gguf mobile 8gb ram pocketpal android ios pipeline tag: text generation 📱 Gemma Magazine 2B M…
Runs locally from ~1.52 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma-magazine-mobile.gguf | GGUF | GGUF | 1.52 GB | Download |
Model Details
| Model ID | tinku1102/gemma-magazine-2b-mobile-gguf |
|---|---|
| Author | tinku1102 |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | google/gemma-2-2b-it |
| Last modified | 2026-08-08T09:17:59.000Z |
Model README
---
license: apache-2.0
base_model: google/gemma-2-2b-it
tags:
- gemma
- gguf
- mobile
- 8gb-ram
- pocketpal
- android
- ios
pipeline_tag: text-generation
---
📱 Gemma Magazine 2B Mobile (GGUF for 8GB Phones)
This is a lightweight, mobile-optimized model based on Google Gemma 2 (2B), specifically engineered to run 100% offline on 8GB RAM mobile phones (Android & iOS).
📊 Mobile Benchmark
- File Size: 1.52 GB (GGUF 4-Bit)
- Active RAM Footprint: ~1.5 GB
- Target Devices: Android phones with 6GB/8GB RAM, iPhones (A15+), Snapdragons, MediaTek Dimensity
- Compatibility: PocketPal AI, ChatterUI, LM Studio Mobile, Layla
📲 How to Run in PocketPal AI (Mobile)
- Open PocketPal AI on your phone.
- In the model search, enter:
tinku1102/gemma-magazine-2b-mobile-gguf
- Download
gemma-magazine-mobile.ggufto run 100% offline with zero internet!
💻 How to Run with Ollama
ollama run hf.co/tinku1102/gemma-magazine-2b-mobile-ggufRun tinku1102/gemma-magazine-2b-mobile-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models