license: apache-2.0 base_model: huihui-ai/Huihui-Qwen3.5-9B-abliterated library_name: mlx pipeline_tag: text-generation tags:

• mlx
• 4-bit
• abliterated
• minstrel

Interim Labs Huihui Qwen3.5-9B abliterated MLX 4-bit

This is a text-only, 4-bit affine/group-64 MLX derivative for Minstrel's optional Max · Unbound local language engine. It is based on the pinned vanch007/Huihui-Qwen3.5-9B-abliterated-mlx-4bit snapshot 7b094180782d187b6f76242d085882914e6af181. The signed Minstrel manifest and provenance file are included for slot extended-abliterated-local, artifact version 0.1.0.

The reference abliterated upstream is huihui-ai/Huihui-Qwen3.5-9B-abliterated at 05b9e7c9b978ba29bdb8f50a49c30e4b91183339; the MLX converter does not establish the exact upstream revision it used. Huihui's 9B card does not document TRL fine-tuning. The Apache-2.0 license is copied from Qwen/Qwen3.5-9B at c202236235762e1c871ad0ccb60c8ee5ba337b9a. This package alone does not enable the model in Minstrel or establish writing-quality performance.