Qwen3.8-27B-Abliterated-MLX Model Released on Hugging Face
PocketAiHub · hf · 2026-08-17
The Qwen3.8-27B-Abliterated multimodal model is now available on Hugging Face, optimized for the MLX framework. It supports image-text-to-text pipelines and offers multiple quantization options (2-bit to 8-bit) for efficient local deployment on Apple Silicon hardware.
More from Models
- 前沿智能降价如云存储,企业 AI 竞争转向路由与编排层 — krishnan · 2026-08-18
- DeepSeek-V4-Pro Released with Adjustable Reasoning and OpenAI API Compatibility — petrusenko_max · 2026-08-18
- Microsoft Research: 4B model tuned with SocialRL out-negotiates GPT-5 family — dair_ai · 2026-08-17
- Gemini 3.7 Flash Launches with Temporary Low Pricing — KoseteBamse · 2026-08-17
- New Flash model matches Pro in style and performance — teortaxesTex · 2026-08-17
- GLM-5.3 outperforms Fable 5 in 3D web design with 15x lower cost — togethercompute · 2026-08-17