diff --git a/haystack/nodes/prompt/invocation_layer/hugging_face.py b/haystack/nodes/prompt/invocation_layer/hugging_face.py
index 1705453e7..277d8d4a4 100644
--- a/haystack/nodes/prompt/invocation_layer/hugging_face.py
+++ b/haystack/nodes/prompt/invocation_layer/hugging_face.py
@@ -235,7 +235,6 @@ class HFLocalInvocationLayer(PromptModelInvocationLayer):
             # Thus only generated text is returned (excluding prompt)
             if is_text_generation and "return_full_text" not in model_input_kwargs:
                 model_input_kwargs["return_full_text"] = False
-                model_input_kwargs["max_new_tokens"] = self.max_length
             if stop_words:
                 sw = StopWordsCriteria(tokenizer=self.pipe.tokenizer, stop_words=stop_words, device=self.pipe.device)
                 model_input_kwargs["stopping_criteria"] = StoppingCriteriaList([sw])