XformAI-india/Qwen3-0.6B-coders-gguf

💻 Qwen3-0.6B Coder – GGUF (Local Use Version)

Model: XformAI-india/qwen3-0.6b-coder-gguf
Base Model: Qwen-0.6B Fine-Tuned On: Code generation tasks
Architecture: Transformer decoder (GPT-style)
Parameter Size: 0.6B (~600M)
Quantization: GGUF (e.g., Q4_K_M / Q6_K)
Converted By: XformAI
Date: May 2025
License: Apache 2.0 (inherited from base)

---

🚀 Overview

This is the GGUF-converted version of XformAI-india/qwen3-0.6b-coder, optimized for local inference, including:

• 🔧 llama.cpp
• ⚙️ LM Studio
• 💻 Ollama
• 🐍 KoboldCpp / text-generation-webui

It is trained for task-oriented code generation, covering Python, Bash, HTML, JavaScript, and small app scaffolding.

---

🧱 Model Details

Feature	Value
Model Format	GGUF (Q4, Q5, Q6, etc.)
Model Type	Decoder-only LLM
Base	Qwen 0.5B
Fine-Tune Method	LoRA (code-tasks)
File Sizes	Q4_K_M: ~460MB / Q6: ~800MB
Context Length	2048 tokens
Tokenizer	Compatible with Qwen tokenizer (qwen.tiktoken)

---

🛠 Use Cases

• Lightweight local coding assistants
• VSCode extensions
• CLI & DevOps helpers
• Edge AI programming bots
• Offline developer tools

---

💻 How to Use (locally with llama.cpp)

# Clone llama.cpp if not already
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make

# Run the model
./main -m qwen-0.6b-coder.Q4_K_M.gguf -p "Write a Python script that creates a zip file from a directory."