Nitishsharma9/CyberCoder-Mobile-7B-GGUF overview
CyberCoder Mobile 7B GGUF GGUF quantizations of Qwen2.5 Coder 7B Instruct, a powerful 7B parameter model specifically fine tuned for incredibly fast Python scr…
Runs locally from ~1.77 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| CyberCoder-Mobile-7B-IQ1_S.gguf | GGUF | IQ1_S | 1.77 GB | Download |
Model Details
| Model ID | Nitishsharma9/CyberCoder-Mobile-7B-GGUF |
|---|---|
| Author | Nitishsharma9 |
| Pipeline | — |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-07-15T10:04:42.000Z |
Model README
---
license: apache-2.0
tags:
- qwen
- 7b
- gguf
- cybersecurity
- ethical-hacking
- code-completion
- fim
---
CyberCoder-Mobile-7B-GGUF
GGUF quantizations of Qwen2.5-Coder-7B-Instruct, a powerful 7B parameter model specifically fine-tuned for incredibly fast Python scripting, Fill-in-the-Middle (FIM) code completion, Ethical Hacking, and Cybersecurity operations.
Background
This model serves as a general-purpose reasoning distill specifically tailored for offensive and defensive security contexts. By taking the state-of-the-art Qwen 2.5 Coder 7B base, this model delivers massive reasoning capabilities compressed into a footprint that can run natively on mobile devices (via PocketPal) and PCs with 6GB+ RAM.
Core Capabilities:
- ⚡ Lightning Fast Python Scripting: Optimized to generate robust, production-ready Python tools in milliseconds.
- 🛡️ Ethical Hacking & Cyber Security: Deep knowledge of vulnerability assessment, penetration testing patterns, and defensive engineering.
- 🔄 Fill-in-the-Middle (FIM): Native support for seamless code completion right inside your IDE.
Hardware compatibility (Ultra-Compressed IQ Formats)
| Quantization | Bits | Exact File Size | RAM Required |
| --- | --- | --- | --- |
| IQ1_S | 1.56-bit | ~1.5 GB | ~2.5 GB |
| IQ2_XXS | 2.06-bit | ~1.9 GB | ~3.0 GB |
| IQ2_S | 2.50-bit | ~2.3 GB | ~3.5 GB |
| IQ3_XXS | 3.06-bit | ~2.8 GB | ~4.0 GB |
| Q4_K_M | 4.00-bit | 4.68 GB | ~5.7 GB |
🚀 How to Use
📱 PocketPal (Mobile)
- Download the PocketPal app on your iOS or Android device.
- Navigate to Models -> Add Model -> Hugging Face.
- Search for
Nitishsharma9/CyberCoder-Mobile-7B-GGUF. - Download the
Q2_KorQ3_K_Mfile (these are the best sizes for mobile RAM limits). - Load the model and start chatting entirely offline!
🦙 Ollama (PC/Mac/Linux)
You can run this natively in Ollama. Download your preferred GGUF file (e.g., CyberCoder-Mobile-7B-Q4_K_M.gguf), then create a file named Modelfile with this content:
FROM ./CyberCoder-Mobile-7B-Q4_K_M.gguf
Then build and run:
ollama create CyberCoder -f Modelfile
ollama run CyberCoder
💻 LM Studio / AnythingLLM
- Open LM Studio or your preferred desktop application.
- Search for
Nitishsharma9/CyberCoder-Mobile-7B-GGUFin the search bar. - Select your desired quantization (
Q4_K_Mis highly recommended for 6GB RAM PCs). - Click Download and Load the model!
Run Nitishsharma9/CyberCoder-Mobile-7B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models