diff --git a/python/llm/dev/benchmark/all-in-one/run.py b/python/llm/dev/benchmark/all-in-one/run.py
index 25d3b608..7168e587 100644
--- a/python/llm/dev/benchmark/all-in-one/run.py
+++ b/python/llm/dev/benchmark/all-in-one/run.py
@@ -372,8 +372,12 @@ def run_transformer_int4_gpu(repo_id,
         tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)
         model = model.to('xpu')
     else:
-        model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, load_in_low_bit=low_bit,
-                                                     trust_remote_code=True, use_cache=True).eval()
+        if 'starcoder' in repo_id:
+            model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, load_in_low_bit=low_bit,
+                                                        trust_remote_code=True, use_cache=True, torch_dtype=torch.bfloat16).eval()
+        else:
+            model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, load_in_low_bit=low_bit,
+                                                        trust_remote_code=True, use_cache=True).eval()
         tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
         model = model.to('xpu')
         if isinstance(model, GPTJForCausalLM):
diff --git a/python/llm/test/benchmark/arc-perf-test.yaml b/python/llm/test/benchmark/arc-perf-test.yaml
index c5235419..a5fbe22f 100644
--- a/python/llm/test/benchmark/arc-perf-test.yaml
+++ b/python/llm/test/benchmark/arc-perf-test.yaml
@@ -5,7 +5,7 @@ repo_id:
   - 'tiiuae/falcon-7b-instruct-with-patch'
   - 'mosaicml/mpt-7b-chat'
   - 'redpajama/gptneox-7b-redpajama-bf16'
-  # - 'bigcode/starcoder-15.5b'
+  - 'bigcode/starcoder-15.5b'
   - 'databricks/dolly-v1-6b'
   - 'databricks/dolly-v2-7b'
   - 'databricks/dolly-v2-12b'