qwen3-0.6b-design-sft-gguf

GGUF conversion of chaddy81/qwen3-0.6b-design-sft for local inference with Ollama, LM Studio, or llama.cpp.

Files

File	Quant	Use Case
qwen3-0.6b-design-sft-f16.gguf	F16	Best quality
qwen3-0.6b-design-sft-q8_0.gguf	Q8_0	High quality
qwen3-0.6b-design-sft-q5_k_m.gguf	Q5_K_M	Good balance
qwen3-0.6b-design-sft-q4_k_m.gguf	Q4_K_M	Recommended

Usage with Ollama

huggingface-cli download chaddy81/qwen3-0.6b-design-sft-gguf qwen3-0.6b-design-sft-q4_k_m.gguf
echo "FROM ./qwen3-0.6b-design-sft-q4_k_m.gguf" > Modelfile
ollama create design-model -f Modelfile
ollama run design-model