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/transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63df7ea5de96aae1bcb82c8281a95cda1eb22f2136a7d0882b5aa06394cf495f
-size 2316821699
+oid sha256:f8ca9f9381fd3713aa3aaf70d7c04dc1b1f130643416dc37a70208531b3a36bc
+size 2326259099