Alibaba’s Qwen Launches Qwen3 AI Models in MLX Format With Multiple Quantisation Levels, Available on Hugging Face and ModelScope
Alibaba's Qwen launched its Qwen3 AI models in MLX format along with multiple quantisation levels. These models are now available on popular platforms such as Hugging Face and ModelScope. Learn more about the recently launched models in MLX format.
Alibaba's Qwen announced launching Qwen3 models in MLX format today and also announced different levels. Qwen3 AI models are now available in four quantisation levels, including 4bit, 6bit, 8bit and BF16 - all optimised for MLX framework, an open-source machine learning platform developed by Apple for Mac computers and Apple silicon chips. The Qwen users can access these models via Hugging Face and ModelScope. OpenAI Releases New ChatGPT Search With Improved Accuracy in Responses and Ability To Perform More Complex Searches.
Qwen3 AIÂ Models Launched in MLX FormatÂ
🚀 Excited to launch Qwen3 models in MLX format today!
Now available in 4 quantization levels: 4bit, 6bit, 8bit, and BF16 — Optimized for MLX framework.
👉 Try it now!
Huggingface：https://t.co/ONjw6Ao8SF
ModelScope： https://t.co/zl9ykgJC1W pic.twitter.com/umdQb0WyTP
— Qwen (@Alibaba_Qwen) June 16, 2025
(The above story first appeared on LatestLY on Jun 16, 2025 02:50 PM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).
