marcinrogalski

Qwen3.6-27B-oQ6e-mtp

marcinrogalski/Qwen3.6-27B-oQ6e-mtp

Qwen3.6-27B-oQ6e-mtp is a machine learning model from marcinrogalski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.

This model was quantized using oQ (oMLX v0.5.7) mixed-precision quantization. It's perfect for around 64gb of memory, leaving place for context, cache and having MTP heads for 1.5 faster inference.