diff --git a/src/h3_blackwell_runtime/nvfp4_quant.py b/src/h3_blackwell_runtime/nvfp4_quant.py
index bd23ed6..ab92d3b 100644
--- a/src/h3_blackwell_runtime/nvfp4_quant.py
+++ b/src/h3_blackwell_runtime/nvfp4_quant.py
@@ -51,10 +51,10 @@ def _env_int(name: str, default: int) -> int:
 
 
 def _vortex_scale_geometry(numel: int) -> tuple[int, int]:
-    threads = _env_int("H3_NVFP4_SCALE_THREADS", 256)
+    threads = _env_int("H3_NVFP4_SCALE_THREADS", 128)
     if threads not in {128, 256, 512}:
         raise ValueError(f"H3_NVFP4_SCALE_THREADS must be 128, 256, or 512, got {threads}")
-    default_blocks = min((numel + threads - 1) // threads, 4096)
+    default_blocks = min((numel + threads - 1) // threads, 256)
     blocks = _env_int("H3_NVFP4_SCALE_BLOCKS", default_blocks)
     if blocks <= 0:
         raise ValueError(f"H3_NVFP4_SCALE_BLOCKS must be positive, got {blocks}")