# Request for small sonar model **URL:** \ **Category:** Bug Reports\ **Created:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-for-small-sonar-model/114 "2025-05-15T00:17:35Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![vikvang](https://avatars.discourse-cdn.com/v4/letter/v/67e7ee/32.png) [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Post date:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-for-small-sonar-model/114/1 "2025-05-15T00:17:35Z")
We’re currently using the `llama-3.1-sonar-small-128k-online` model, which is set to be deprecated on 2025-02-22. We’re moving over to the new `sonar` model but noticing it is significantly slower than the legacy small model - it seems to have similar speed to the legacy large model. For our use case speed it rather critical… are there any plans to release a smaller, faster variation of the `sonar` model? ---
**Author:** ![vikvang](https://avatars.discourse-cdn.com/v4/letter/v/67e7ee/32.png) [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Post date:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-for-small-sonar-model/114/2 "2025-05-15T00:17:37Z")
I also ask for the mini model when I test the answers in the current Sonar, for my language (Polish) the better answers were in the older model than in Sonar and it actually works much faster, when I have a csv file with 150 queries the earlier model worked faster with the current one it takes a little too long to do so ---
**Author:** ![vikvang](https://avatars.discourse-cdn.com/v4/letter/v/67e7ee/32.png) [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Post date:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-for-small-sonar-model/114/3 "2025-05-15T00:17:40Z")
+1 for this feature request, real need for a 7/8B parameter model for low latency responses, or the existing sonar model inference significantly increased.