diff --git a/tests/pipelines/test_nli.py b/tests/pipelines/test_nli.py
index 0fb0bd2b..0c8da8b4 100644
--- a/tests/pipelines/test_nli.py
+++ b/tests/pipelines/test_nli.py
@@ -7,6 +7,7 @@ from modelscope.models.nlp import SbertForNLI
 from modelscope.pipelines import NLIPipeline, pipeline
 from modelscope.preprocessors import NLIPreprocessor
 from modelscope.utils.constant import Tasks
+from modelscope.utils.test_utils import test_level
 
 
 class NLITest(unittest.TestCase):
@@ -14,8 +15,8 @@ class NLITest(unittest.TestCase):
     sentence1 = '四川商务职业学院和四川财经职业学院哪个好？'
     sentence2 = '四川商务职业学院商务管理在哪个校区？'
 
-    @unittest.skip('skip temporarily to save test time')
-    def test_run_from_local(self):
+    @unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
+    def test_run_with_direct_file_download(self):
         cache_path = snapshot_download(self.model_id)
         tokenizer = NLIPreprocessor(cache_path)
         model = SbertForNLI(cache_path, tokenizer=tokenizer)
@@ -28,6 +29,7 @@ class NLITest(unittest.TestCase):
             f'sentence1: {self.sentence1}\nsentence2: {self.sentence2}\n'
             f'pipeline1: {pipeline2(input=(self.sentence1, self.sentence2))}')
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_from_modelhub(self):
         model = Model.from_pretrained(self.model_id)
         tokenizer = NLIPreprocessor(model.model_dir)
@@ -35,10 +37,12 @@ class NLITest(unittest.TestCase):
             task=Tasks.nli, model=model, preprocessor=tokenizer)
         print(pipeline_ins(input=(self.sentence1, self.sentence2)))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_name(self):
         pipeline_ins = pipeline(task=Tasks.nli, model=self.model_id)
         print(pipeline_ins(input=(self.sentence1, self.sentence2)))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_default_model(self):
         pipeline_ins = pipeline(task=Tasks.nli)
         print(pipeline_ins(input=(self.sentence1, self.sentence2)))
diff --git a/tests/pipelines/test_sentiment_classification.py b/tests/pipelines/test_sentiment_classification.py
index 7e55cd4c..0ba22d5c 100644
--- a/tests/pipelines/test_sentiment_classification.py
+++ b/tests/pipelines/test_sentiment_classification.py
@@ -7,13 +7,15 @@ from modelscope.models.nlp import SbertForSentimentClassification
 from modelscope.pipelines import SentimentClassificationPipeline, pipeline
 from modelscope.preprocessors import SentimentClassificationPreprocessor
 from modelscope.utils.constant import Tasks
+from modelscope.utils.test_utils import test_level
 
 
 class SentimentClassificationTest(unittest.TestCase):
     model_id = 'damo/nlp_structbert_sentiment-classification_chinese-base'
     sentence1 = '启动的时候很大声音，然后就会听到1.2秒的卡察的声音，类似齿轮摩擦的声音'
 
-    def test_run_from_local(self):
+    @unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
+    def test_run_with_direct_file_download(self):
         cache_path = snapshot_download(self.model_id)
         tokenizer = SentimentClassificationPreprocessor(cache_path)
         model = SbertForSentimentClassification(
@@ -30,6 +32,7 @@ class SentimentClassificationTest(unittest.TestCase):
         print(f'sentence1: {self.sentence1}\n'
               f'pipeline1: {pipeline2(input=self.sentence1)}')
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_from_modelhub(self):
         model = Model.from_pretrained(self.model_id)
         tokenizer = SentimentClassificationPreprocessor(model.model_dir)
@@ -39,11 +42,13 @@ class SentimentClassificationTest(unittest.TestCase):
             preprocessor=tokenizer)
         print(pipeline_ins(input=self.sentence1))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_name(self):
         pipeline_ins = pipeline(
             task=Tasks.sentiment_classification, model=self.model_id)
         print(pipeline_ins(input=self.sentence1))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_default_model(self):
         pipeline_ins = pipeline(task=Tasks.sentiment_classification)
         print(pipeline_ins(input=self.sentence1))
diff --git a/tests/pipelines/test_zero_shot_classification.py b/tests/pipelines/test_zero_shot_classification.py
index 278ce419..236013aa 100644
--- a/tests/pipelines/test_zero_shot_classification.py
+++ b/tests/pipelines/test_zero_shot_classification.py
@@ -7,6 +7,7 @@ from modelscope.models.nlp import SbertForZeroShotClassification
 from modelscope.pipelines import ZeroShotClassificationPipeline, pipeline
 from modelscope.preprocessors import ZeroShotClassificationPreprocessor
 from modelscope.utils.constant import Tasks
+from modelscope.utils.test_utils import test_level
 
 
 class ZeroShotClassificationTest(unittest.TestCase):
@@ -15,7 +16,8 @@ class ZeroShotClassificationTest(unittest.TestCase):
     labels = ['文化', '体育', '娱乐', '财经', '家居', '汽车', '教育', '科技', '军事']
     template = '这篇文章的标题是{}'
 
-    def test_run_from_local(self):
+    @unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
+    def test_run_with_direct_file_download(self):
         cache_path = snapshot_download(self.model_id)
         tokenizer = ZeroShotClassificationPreprocessor(cache_path)
         model = SbertForZeroShotClassification(cache_path, tokenizer=tokenizer)
@@ -36,6 +38,7 @@ class ZeroShotClassificationTest(unittest.TestCase):
             f'pipeline2: {pipeline2(self.sentence,candidate_labels=self.labels,hypothesis_template=self.template)}'
         )
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_from_modelhub(self):
         model = Model.from_pretrained(self.model_id)
         tokenizer = ZeroShotClassificationPreprocessor(model.model_dir)
@@ -45,11 +48,13 @@ class ZeroShotClassificationTest(unittest.TestCase):
             preprocessor=tokenizer)
         print(pipeline_ins(input=self.sentence, candidate_labels=self.labels))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_model_name(self):
         pipeline_ins = pipeline(
             task=Tasks.zero_shot_classification, model=self.model_id)
         print(pipeline_ins(input=self.sentence, candidate_labels=self.labels))
 
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
     def test_run_with_default_model(self):
         pipeline_ins = pipeline(task=Tasks.zero_shot_classification)
         print(pipeline_ins(input=self.sentence, candidate_labels=self.labels))