sc-15071: regenerate the q4 tier with the 8-bit precision floors

The previous q4 artifact was packed uniformly at 4 bits, which made the tier render a repeating tiled texture instead of the prompt. norm_out.linear (the output head's adaLN modulation) and the Qwen3-VL LM decoder layers are now packed at 8 bits; everything else is unchanged. q8 and bf16 are untouched.

q4/README.md

@@ -14,7 +14,7 @@ tags:
 <h1 align="center">Mage-Flow<br><span style="font-size: 0.55em; font-weight: normal;">An Efficient Native-Resolution Foundation Model for Image Generation and Editing</span></h1>
 
 <p align="center">
-  <a href="https://github.com/microsoft/Mage/blob/main/assets/mage_flow_tech_report.pdf"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--Flow-b31b1b" height="22" /></a>
+  <a href="https://arxiv.org/abs/2607.19064"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--Flow-b31b1b" height="22" /></a>
   <a href="https://microsoft.github.io/Mage"><img alt="Project Page" src="https://img.shields.io/badge/%F0%9F%8C%90-Project%20Page-blue" height="22" /></a>
   <a href="https://github.com/microsoft/Mage"><img src="https://img.shields.io/badge/Code-GitHub-181717?logo=github" alt="GitHub"></a>
   <a href="https://huggingface.co/microsoft/Mage-Flow-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Base-yellow" height="22" /></a>

q4/transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad8655960bdfe28e7b14154a3b8be8de0ebe2abc7b9375e4070c7fbe9f21f35
-size 2316821829
+oid sha256:f5a0241588d4528d1462ee960bc9c70dede1b6103817494dea9424781c619b70
+size 2326258965