Basic information
Model repository: rapid-mlx/Qwen3.8-Flash-Next-4bit
Organization: rapid-mlx
Tasks: text-generation
Architecture and runtime
Model type: qwen4_exp
Architecture: Qwen4ExpForConditionalGeneration
Libraries: mlx, safetensors, pytorch
Base models: Qwen/Qwen3.8-Flash-Next
Current revision: master
License and update history
License: qwen-community-1.0
Created: 2026-09-03
Last updated: 2026-10-15
Hardware requirements
Not filled in locally.
Download links
Not filled in locally.
Basic usage example
Not filled in locally.