# A Refusal-Stripped Qwen3.8-27B Build Now Runs Locally on Apple Silicon

The MLX release includes 2, 4, 6 and 8-bit quantized versions of a 27-billion-parameter vision-language model whose safety training has been removed by canceling out the internal signal linked to refusal.

- Published: 2026-08-19T06:20:14.557Z
- Canonical: https://polylog.news/ai/2026-08-19/a-refusal-stripped-qwen3-8-27b-build-now-runs-locally-on-app
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

A modified build of Alibaba's Qwen3.8-27B model appeared on Hugging Face packaged for Apple's MLX framework, software that runs models directly on Apple Silicon's shared memory rather than on a separate graphics processor. The repository do…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-19/a-refusal-stripped-qwen3-8-27b-build-now-runs-locally-on-app (subscription information: https://polylog.news/pricing).