Qwen/Qwen3-0.6B-MLX-bf16
TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:May 23, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Qwen3-0.6B-MLX-bf16 is a 0.6 billion parameter causal language model from the Qwen3 series, developed by Qwen. This model uniquely supports seamless switching between a 'thinking mode' for complex reasoning, math, and coding, and a 'non-thinking mode' for efficient general dialogue. It demonstrates significant enhancements in reasoning capabilities, superior human preference alignment for creative writing and role-playing, and strong agent capabilities with tool integration, alongside multilingual support for over 100 languages.

Loading preview...