diff --git a/.github/workflows/pull.yml b/.github/workflows/pull.yml
index eb1a414531b..eb65968ab1a 100644
--- a/.github/workflows/pull.yml
+++ b/.github/workflows/pull.yml
@@ -856,7 +856,7 @@ jobs:
         mode: [qnn]
       fail-fast: false
     with:
-      runner: linux.2xlarge
+      runner: linux.4xlarge.memory
       docker-image: ci-image:executorch-ubuntu-22.04-qnn-sdk
       submodules: 'recursive'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
diff --git a/backends/qualcomm/quantizer/quantizer.py b/backends/qualcomm/quantizer/quantizer.py
index c6fbc51484f..c21f9d90411 100644
--- a/backends/qualcomm/quantizer/quantizer.py
+++ b/backends/qualcomm/quantizer/quantizer.py
@@ -416,7 +416,12 @@ def _get_quant_range(self, node):
                 if quant_info.output_qspec.quant_min is None
                 else quant_info.output_qspec.quant_min
             )
-            return quant_range
+            # Cap the inf stand-in so it does not dominate the tensor's
+            # dynamic range.  For >8-bit activations the full range (e.g.
+            # 65535 for uint16) would blow up the attention-mask quant scale
+            # and wreck accuracy; 255 keeps a reasonable scale for
+            # Llama-style attention masks.
+            return min(quant_range, 255)
 
     def _get_candidates_with_infinity_args(self, graph_module: GraphModule):
         binary_op_sources = [