Qwen 3.8 27B Uncensored MLX build released for Mac
dr_cintas · x · 2026-08-19
OrcaRouter has released an official MLX build of Qwen 3.8 27B Uncensored.
Key Features:
- Supports local, uncensored execution.
- Multiple quantization options available (2-bit, 4-bit, 6-bit, & 8-bit) to balance RAM and speed.
- No CUDA or cloud required; runs directly on Mac with weights.
Related event: Uncensored Qwen3.8-27B MLX Build Released for Apple Silicon(4 posts)→
More from Infra
- Sovereign wealth funds may bankroll AI infra as traditional capital dries up — abhiadesai · 2026-08-19
- Steel mill consumed 50% as much water as all US data centers combined — AndyMasley · 2026-08-19
- PA Governor signs executive order implementing strictest AI data center standards — ivan_bezdomny · 2026-08-19
- Manzanas: Open Source MCP Server for AI Agents to Control iOS Simulators — Plastic-Risk-6309 · 2026-08-19
- Baidu serves DeepSeek V4 Flash at crazy fast speeds and low prices — NielsRogge · 2026-08-19
- Home-Based GPU Networks: Viable Supplements to AI Data Centers? — CackleRooster · 2026-08-19