Refusal-Removed Qwen3.8-27B Runs Locally on Apple Silicon with Zero Refusals
JOBhakdi · x · 2026-08-19
A "refusal-removed" version of Qwen3.8-27B has been released with open weights, runnable locally on Apple Silicon. Built as an MLX release in 2, 4, 6 and 8-bit versions, the uploader claims 4/6/8-bit tests produced zero refusals while preserving vision, reasoning and tool-calling across a 262K-token context.
The poster argues this is a landmark moment: a highly capable frontier open-weights model is now locally available with no guardrails at all, with implications far larger than currently realized—and society needs to discuss it.
Related event: Uncensored Qwen3.8-27B MLX Build Released for Apple Silicon(4 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16