diff --git a/executorch-patches/qwen3_4b_decoder.patch b/executorch-patches/qwen3_4b_decoder.patch
index 91b6c34..e7049ef 100644
--- a/executorch-patches/qwen3_4b_decoder.patch
+++ b/executorch-patches/qwen3_4b_decoder.patch
@@ -1,5 +1,5 @@
 diff --git a/examples/qualcomm/oss_scripts/llama/__init__.py b/examples/qualcomm/oss_scripts/llama/__init__.py
-index 963db6e..953dc4c 100644
+index 963db6e..9ccfdd0 100644
 --- a/examples/qualcomm/oss_scripts/llama/__init__.py
 +++ b/examples/qualcomm/oss_scripts/llama/__init__.py
 @@ -25,9 +25,14 @@ from executorch.examples.models.granite import (
@@ -20,7 +20,7 @@ index 963db6e..953dc4c 100644
  from executorch.examples.models.qwen2_5 import (
      convert_weights as convert_qwen2_5_weights,
  )
-@@ -479,6 +484,34 @@ class Qwen3_1_7B(LLMModelConfig):
+@@ -479,6 +484,37 @@ class Qwen3_1_7B(LLMModelConfig):
      quant_recipe = Qwen3_1_7BQuantRecipe
  
  
@@ -40,10 +40,13 @@ index 963db6e..953dc4c 100644
 +    convert_weights = convert_qwen3_weights
 +    transform_weight = False
 +    instruct_model = True
-+    # Bumped to 2 to halve peak host RAM during QNN compile (4B at sharding=1
-+    # OOMed on a 62 GB box, peak anon-rss 46 GB). At sharding=2 each shard
-+    # compile fits comfortably; runner stitches them at load time.
-+    num_sharding = 2
++    # num_sharding=1 for hybrid mode: sharding=2 produces a multi-context
++    # .pte (2 graphs × 2 shards = 4 contexts) that the LlmModule load path
++    # can't restore (error 5010 "Context group 1 does not exist"). With
++    # sharding=1 the hybrid export needs ~46 GB RAM peak — the 192 GB swap
++    # on /swapfile handles this; compile takes ~80 min wall but completes
++    # cleanly. Single-context .pte loads fine through the JNI runner.
++    num_sharding = 1
 +    masked_softmax = True
 +    seq_mse_candidates = 0
 +    r1 = False