Qwen/Qwen3-8B-MLX-bf16

Warm
Public
8B
FP8
32768
1
May 23, 2025
License: apache-2.0
Hugging Face

Qwen/Qwen3-8B-MLX-bf16 is an 8.2 billion parameter causal language model from the Qwen series, developed by Qwen. This model uniquely supports seamless switching between a 'thinking mode' for complex logical reasoning, math, and coding, and a 'non-thinking mode' for efficient general-purpose dialogue. It delivers enhanced reasoning capabilities, superior human preference alignment for creative writing and role-playing, and strong agent capabilities with multilingual support for over 100 languages.

No reviews yet. Be the first to review!