Uncensored Qwen 3.8 27B MLX Build Released for Apple Silicon with Multiple Quantization Levels
alexcovo_eth · x · 2026-08-18
OrcaRouter released an uncensored MLX build of Qwen's 27B model tailored for Apple Silicon. The abliterated model removes safety refusals and is available in 2/4/6/8-bit quantization, running locally without CUDA or cloud dependencies. It retains vision-language, function-calling, and reasoning capabilities.
Related event: Uncensored Qwen3.8-27B MLX Build Released for Apple Silicon(4 posts)→
More from Models
- LLM-as-a-Verifier lifts Nemotron 3.5 Super by 9-10 points on agentic benchmarks — simonguozirui · 2026-10-16
- Bonsai 2 ternary models tested: 4B is the sweet spot, but 27B unexpectedly fumbles file writes — cephaloform · 2026-10-16
- Meta's Omnilingual ASR, covering 1,600 languages, named a TIME Best Invention of 2026 — AIatMeta · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16
- ChatGPT's quality slips: broken extension and endless Computer Use permission prompts — sytelus · 2026-10-16