diff --git a/docs/resources/models.mdx b/docs/resources/models.mdx
index 79daf09c5..93518e2e1 100644
--- a/docs/resources/models.mdx
+++ b/docs/resources/models.mdx
@@ -11,7 +11,7 @@ We currently only support the following model for serverless training. We are ac
 
 - [OpenPipe Qwen 3 14B Instruct](https://huggingface.co/OpenPipe/Qwen3-14B-Instruct)
   - Good balance of performance and size. Has support for tool calling and generally trains well. This is our recommended model for users new to RL.
-- [OpenPipe Qwen 3 30B Instruct](https://huggingface.co/OpenPipe/Qwen3-30B-Instruct)
+- [Qwen 3 30B A3B Instruct](https://huggingface.co/Qwen/Qwen3-30B-A3B)
   - More capable than 14B while still being efficient. Good choice when you need stronger reasoning capabilities.