Uncensored Qwen3.8-27B Released for Apple Silicon via MLX

OrcaRouter has released Qwen3.8-27B-Uncensored-MLX, trending on Hugging Face. The safety-alignment-removed model, built with abliteration, offers 2-bit to 8-bit quantization options optimized for local Apple Silicon deployment.

2026-08-18 ~ 2026-08-18 · 2 related posts

• Uncensored Qwen 3.8 27B MLX Build Released for Apple Silicon with Multiple Quantization Levels — alexcovo_eth · 2026-08-18
• Qwen3.8-27B Uncensored MLX build trends on Hugging Face for Apple Silicon — orcarouter · 2026-08-18