GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

PocketWeights/Qwen2.5-Coder-7B-Instruct-GGUF-6GB overview

⚡ PocketWeights: Qwen 2.5 Coder 7B Instruct 6GB VRAM Edition Heavy models, made light. We specialize in high quality GGUF quantizations optimized for edge devi…

ggufqwen2.5codequantizedbase_model:Qwen/Qwen2.5-Coder-7B-Instructbase_model:quantized:Qwen/Qwen2.5-Coder-7B-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~4.36 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
173
Likes
0
Pipeline

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Qwen2.5-Coder-7B-Instruct-GGUF-6GB-Q4_K_M.ggufGGUFQ4_K_M4.36 GBDownload

Model Details

Model IDPocketWeights/Qwen2.5-Coder-7B-Instruct-GGUF-6GB
AuthorPocketWeights
Pipeline
Licenseapache-2.0
Base modelQwen/Qwen2.5-Coder-7B-Instruct
Last modified2026-08-03T15:00:08.000Z

Model README

---

base_model: Qwen/Qwen2.5-Coder-7B-Instruct

library_name: gguf

license: apache-2.0

tags:

- gguf

- qwen2.5

- code

- quantized

---

⚡ PocketWeights: Qwen 2.5 Coder 7B Instruct (6GB VRAM Edition)

Heavy models, made light. We specialize in high-quality GGUF quantizations optimized for edge devices and gaming laptops.

What is this model?

This is a heavily optimized GGUF of Qwen2.5-Coder-7B-Instruct. It preserves 99% of the coding logic but shrinks the massive 15GB model down to fit easily onto a laptop, making it the perfect offline coding assistant.

📦 Pick Your Hardware

We bypass the confusing wall of files to provide specific sizes optimized for your hardware:

  • Q4_K_M (Fits 6GB VRAM): The standard. Perfect for RTX 3060/4050.

🚀 Quick Start Guide

Option 1: LM Studio (Easiest)

  1. Download & open LM Studio.
  2. In the search bar, type: PocketWeights/Qwen2.5-Coder-7B-Instruct-GGUF-6GB.
  3. Select your hardware size, click Download, and hit Play!

Option 2: Ollama

If you have Ollama installed, simply run this command in your terminal:

ollama run hf.co/PocketWeights/Qwen2.5-Coder-7B-Instruct-GGUF-6GB:Q4_K_M

Run PocketWeights/Qwen2.5-Coder-7B-Instruct-GGUF-6GB with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models