diff --git a/backends/arm/test/models/test_T5ForConditionalGeneration_arm.py b/backends/arm/test/models/test_T5ForConditionalGeneration_arm.py
index 222be958b09..7daba1f7003 100644
--- a/backends/arm/test/models/test_T5ForConditionalGeneration_arm.py
+++ b/backends/arm/test/models/test_T5ForConditionalGeneration_arm.py
@@ -114,7 +114,8 @@ def test_t5_for_conditional_generation_tosa_INT():
             aten_op=[],
             exir_op=[],
             use_to_edge_transform_and_lower=True,
-            atol=5,  # TODO: MLETORCH-1703: Reduce the tolerance of quantized T5ForConditionalGeneration
+            atol=14,  # TODO: MLETORCH-1703: Reduce the tolerance of quantized T5ForConditionalGeneration
+            frobenius_threshold=0.3,
         )
         pipeline.change_args(
             "check_count.exir",
@@ -161,7 +162,7 @@ def test_t5_for_conditional_generation_vgf_quant():
             aten_op=[],
             exir_op=[],
             use_to_edge_transform_and_lower=True,
-            atol=5,  # TODO: MLETORCH-1703: Reduce the tolerance of quantized T5ForConditionalGeneration
+            atol=14,  # TODO: MLETORCH-1703: Reduce the tolerance of quantized T5ForConditionalGeneration
             quantize=True,
         )
         pipeline.change_args(
diff --git a/backends/arm/test/models/test_inception_v3_arm.py b/backends/arm/test/models/test_inception_v3_arm.py
index f842ea1f265..e71bb960bb3 100644
--- a/backends/arm/test/models/test_inception_v3_arm.py
+++ b/backends/arm/test/models/test_inception_v3_arm.py
@@ -56,7 +56,7 @@ def test_ic3_tosa_FP_fp16():
         aten_op=[],
         exir_op=[],
         use_to_edge_transform_and_lower=True,
-        atol=5e-2,
+        atol=0.2,
     )
     pipeline.run()
 
diff --git a/backends/arm/test/ops/test_conv2d.py b/backends/arm/test/ops/test_conv2d.py
index 90c53793caf..ed17b3cb994 100644
--- a/backends/arm/test/ops/test_conv2d.py
+++ b/backends/arm/test/ops/test_conv2d.py
@@ -510,6 +510,8 @@ def test_convolution_2d_tosa_FP(test_data):
         aten_op,
         exir_op,
         tosa_extensions=["bf16"],
+        atol=3e-3,
+        rtol=3e-3,
     )
     pipeline.run()
 
@@ -620,6 +622,8 @@ def test_convolution_2d_vgf_no_quant(test_data):
         aten_op,
         exir_op,
         quantize=False,
+        atol=3e-3,
+        rtol=3e-3,
     )
     pipeline.run()
 
diff --git a/backends/arm/test/ops/test_upsample_bilinear2d.py b/backends/arm/test/ops/test_upsample_bilinear2d.py
index 6d7b1711ca2..95cf57af98a 100644
--- a/backends/arm/test/ops/test_upsample_bilinear2d.py
+++ b/backends/arm/test/ops/test_upsample_bilinear2d.py
@@ -426,6 +426,8 @@ def test_upsample_bilinear2d_vec_vgf_no_quant_UpsamplingBilinear2d(
         aten_op,
         exir_op,
         quantize=False,
+        atol=2e-3,
+        rtol=2e-3,
     )
     if not compare:
         pipeline.pop_stage(-1)