jc-builds/Qwen3-0.6B-Q4_K_M-GGUF

Qwen3-0.6B Q4_K_M GGUF

This is a Q4_K_M quantized GGUF conversion of Qwen/Qwen3-0.6B optimized for on-device inference with llama.cpp.

Model Details

Property	Value
Original Model	Qwen3-0.6B
Parameters	600 million
Quantization	Q4_K_M (4-bit, medium quality)
File Size	~400 MB
Context Window	32,768 tokens
Architecture	Qwen3 (RoPE, SwiGLU, RMSNorm, GQA)

Intended Use

This model is optimized for:

• Mobile/Edge Deployment: Runs efficiently on all iOS devices including older models
• llama.cpp Integration: Compatible with llama.cpp and its bindings
• On-Device AI: Private, offline inference without cloud dependencies

Capabilities

• Ultra-fast inference
• Basic conversation and Q&A
• Simple text tasks
• Multilingual support
• Minimal resource usage

Usage with llama.cpp

./llama-cli -m Qwen3-0.6B-Q4_K_M.gguf -p "Your prompt here" -n 512

License

This model inherits the Apache 2.0 license from the original Qwen3 model.

Attribution

• Original Model: Qwen3-0.6B by Qwen Team, Alibaba Cloud
• Quantization: jc-builds