AI Library
Model Information & Download
Model Options:
125b-a6b-nvfp4 (105GB)
125b-a6b-q4_K_M (120GB)
125b-a6b-q8_0 (189GB)
125b-a6b-bf16 (355GB)
125b-a6b-mlx-bf16 (360GB)
125b-mlx (105GB)
Model Tag:
qwen3.8-flash-next
📋
This experimental preview of the architecture that will underpin Qwen4.
Model File Size
105 GB
Quantization
Q4
License
Not available
Last Updated
2026-09-06 (3 weeks ago)
Tutorial
Download and Run on your PC
← Back to Model Library
