Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release (https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit)
High-quality Q8_0 GGUF quantized conversion of XHToken’s Spark-X2.5-4B, converted, tested, and packaged for Ollama by Yousef Burhan Ahmad.