# Load times for NLU Model Interpreter

**URL:** <https://forum.rasa.com/t/load-times-for-nlu-model-interpreter/41162>\
**Category:** Rasa Open Source\
**Created:** [March 11, 2021, 1:15pm UTC](https://forum.rasa.com/t/load-times-for-nlu-model-interpreter/41162 "2021-03-11T13:15:23Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![adai183](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/adai183/32/12886_2.png) [@adai183](https://forum.rasa.com/u/adai183)\
**Post date:** [March 11, 2021, 1:15pm UTC](https://forum.rasa.com/t/load-times-for-nlu-model-interpreter/41162/1 "2021-03-11T13:15:23Z")

</div>

I have been doing some performance tests for model loading of DIETClassifiers without pre-trained word vectors. Looks like there is a lot of smart caching / loading going on. Does anybody know why loading the first model is so much slower than the latter ones? Also is there a way to speed up the load time for the very first model?

@koaning would be awesome if you could point me in the right direction.

```
from pathlib import Path
import time
from rasa.nlu.model import Interpreter

load_times = []
for model_path in Path("./models_10").glob("*"):
    start = time.time()
    nlu_interpreter = Interpreter.load(model_path)
    load_times.append(time.time() - start)
print(load_times)
>>>>>>>>>
[4.209419012069702, 1.2521369457244873, 1.2520649433135986, 1.256606101989746, 1.4406280517578125, 1.234318733215332, 1.238109827041626, 1.2923908233642578, 1.4882800579071045]
```

---

<div class="post-metadata">

**Author:** ![koaning](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/koaning/32/6626_2.png) [@koaning](https://forum.rasa.com/u/koaning)\
**Post date:** [March 12, 2021, 8:23am UTC](https://forum.rasa.com/t/load-times-for-nlu-model-interpreter/41162/2 "2021-03-12T08:23:12Z")

</div>

I think it’s Tensorflow.

When you run `rasa` from the command line there’s also a unconfortable waiting time. That’s because tensorflow needs to load. You can check locally, the tensorflow payload on disk is typically about 700MB in your virtualenv.