# process killed qiime 2024.5 on Ubuntu 24.04.4 LTS when running on multicore
**URL:** https://forum.qiime2.org/t/process-killed-qiime-2024-5-on-ubuntu-24-04-4-lts-when-running-on-multicore/34053
**Category:** Technical Support
**Tags:** feature-classifier
**Created:** [March 11, 2026, 8:27am UTC](https://forum.qiime2.org/t/process-killed-qiime-2024-5-on-ubuntu-24-04-4-lts-when-running-on-multicore/34053 "2026-03-11T08:27:33Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@scilexenko](https://forum.qiime2.org/u/scilexenko)
#### Post date: [March 11, 2026, 8:27am UTC](https://forum.qiime2.org/t/process-killed-qiime-2024-5-on-ubuntu-24-04-4-lts-when-running-on-multicore/34053/1 "2026-03-11T08:27:34Z")
Hello,
My `classify-sklearn` run is being **killed** due to OOM (Out of Memory) despite having 192GB of RAM. The input `rep-seqs` file is small (8,331 sequences), but the system monitor shows 100% RAM and Swap usage before the process is terminated.
**Command:**
```auto
qiime feature-classifier classify-sklearn \
--i-classifier unite_ver10_97_s_all_04.04.2024-Q2-2024.5.qza \
--i-reads rep-seqs-dada2.qza \
--o-classification taxonomy-ITS.qza \
--p-n-jobs 12 \
--verbose
```
**Rep-Seq Stats:**
- **Count:** 8,331
- **Mean Length:** 278.7 bp
- **Range:** 200–388 bp
**System Info:**
- **CPU:** Intel Core Ultra 9 275HX (24 cores)
- **RAM:** 192GB (100% utilized during crash)
- **Swap:** 8.6GB (100% utilized during crash)
I then tried to run on a single core with a reduced batch size:
```auto
qiime feature-classifier classify-sklearn \
--i-classifier unite_ver10_97_s_all_04.04.2024-Q2-2024.5.qza \
--i-reads rep-seqs-dada2.qza \
--o-classification taxonomy-ITS.qza \
--p-n-jobs 1 \
--p-reads-per-batch 1000 \
--verbose
```
And it worked. The issue was resolved by reducing --p-n-jobs from 12 to 1. Are there specific `scikit-learn` or environment configurations (e.g., `JOBLIB_TEMP_FOLDER`) that can mitigate this memory multiplication in QIIME 2? Why did parallelization terminate the process? How does QIIME manage caching? I previously ran a similar analysis on an M2 Mac without issues, even though it only had 16 GB of RAM.
Thank you,
Ivan
---
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [March 11, 2026, 6:16pm UTC](https://forum.qiime2.org/t/process-killed-qiime-2024-5-on-ubuntu-24-04-4-lts-when-running-on-multicore/34053/2 "2026-03-11T18:16:44Z")
Hello Ivan,
Is there any chance that this is [a database I released (unite-train)](https://github.com/colinbrislawn/unite-train/releases)?
If so, I trained it to include all `sh_` suffixes for species hypotheses (SH).
Having all level 7 labels be unique increases memory usage a lot!
In my new version, I remove the species hypotheses suffix and it needs less RAM to run. If you are using my old database, try my new database:
> **[Release UNITE v10.0 2025-02-19 for qiime2-2026.1 · colinbrislawn/unite-train](https://github.com/colinbrislawn/unite-train/releases/tag/v10.0-2025-02-19-qiime2-2026.1)**
>
> ⚠️ This is a public demo, and has not been validated. I am not affiliated with the UNITE team.
> This is a classifier for Unite v10.0 Version 19.02.2025 trained for use with qiime2-amplicon-2026.1 --...
* * *
> [@scilexenko](#):
>
> mitigate this memory multiplication
This particular Qiime2 plugin is could be improved, see [Utilize one database instance for multiple classification jobs · Issue #190 · qiime2/q2-feature-classifier · GitHub](https://github.com/qiime2/q2-feature-classifier/issues/190)
If you have the python skill, take a look!
---
### Author:  [@system](https://forum.qiime2.org/u/system)
#### Post date: [April 12, 2026, 12:17am UTC](https://forum.qiime2.org/t/process-killed-qiime-2024-5-on-ubuntu-24-04-4-lts-when-running-on-multicore/34053/3 "2026-04-12T00:17:09Z")
This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.