# Question regarding RASA NLU run time **URL:** \ **Category:** Rasa Open Source\ **Created:** [February 14, 2023, 2:09pm UTC](https://forum.rasa.com/t/question-regarding-rasa-nlu-run-time/57206 "2023-02-14T14:09:56Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![matan\_zuckerman](https://avatars.discourse-cdn.com/v4/letter/m/f475e1/32.png) [@matan\_zuckerman](https://forum.rasa.com/u/matan_zuckerman)\ **Post date:** [February 14, 2023, 2:09pm UTC](https://forum.rasa.com/t/question-regarding-rasa-nlu-run-time/57206/1 "2023-02-14T14:09:56Z")
Hi everyone. I’m running Rasa NLU in production on the following spec: GCP e2-standard-8 machine - From which RASA is allocated the following: 4 CPU, 26 GB RAM **Config** : pipeline: - name: SpacyNLP model: “en\_core\_web\_lg” case\_sensitive: False - name: SpacyTokenizer - name: RegexFeaturizer - name: LanguageModelFeaturizer model\_name: “bert” model\_weights: “rasa/LaBSE” - name: CountVectorsFeaturizer analyzer: “char\_wb” min\_ngram: 1 max\_ngram: 4 - name: DIETClassifier model\_confidence: softmax epochs: 100 batch\_strategy: balanced constrain\_similarities: True - name: EntitySynonymMapper - name: SpacyEntityExtractor case\_sensitive: False - name: EntitySynonymMapper - name: CRFEntityExtractor - name: “DucklingEntityExtractor” For each RASA classification (Intent prediction + entity extraction) it takes in average and median ~0.24 second. Is that considered a reasonable running time? Can we speed up the process? Thank you! ---
**Author:** ![stephens](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/stephens/32/1632_2.png) [@stephens](https://forum.rasa.com/u/stephens)\ **Post date:** [March 19, 2023, 4:33pm UTC](https://forum.rasa.com/t/question-regarding-rasa-nlu-run-time/57206/2 "2023-03-19T16:33:19Z")
Rasa Pro supports tracing to see a detailed breakdown of component performance for both training and prediction. You could also look at using a lighter weight pipeline like the LogisticRegressionClassifier.