# MAX Nightly 26.7.0.dev2026092105 (Mojo 1.2.0.dev2026092105) Released

**URL:** <https://forum.modular.com/t/max-nightly-26-7-0-dev2026092105-mojo-1-2-0-dev2026092105-released/3517>\
**Category:** Nightly\
**Created:** [September 21, 2026, 6:45am UTC](https://forum.modular.com/t/max-nightly-26-7-0-dev2026092105-mojo-1-2-0-dev2026092105-released/3517 "2026-09-21T06:45:34Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Modular](https://sea1.discourse-cdn.com/flex001/user_avatar/forum.modular.com/modular/32/17_2.png) [@Modular](https://forum.modular.com/u/Modular)\
**Post date:** [September 21, 2026, 6:45am UTC](https://forum.modular.com/t/max-nightly-26-7-0-dev2026092105-mojo-1-2-0-dev2026092105-released/3517/1 "2026-09-21T06:45:34Z")

</div>

🧑‍🚀 A new nightly version has been released! 🧑‍🚀

See the quickstart guide for installation instructions: [Quickstart | MAX](https://max.modular.com/get-started/#set-up-your-project)

MAX changelog updates:

- Fixed a crash serving Gemma 4, Gemma 3 multimodal, Pixtral, and Qwen 3  
embedding with a batch larger than one. Each of these architectures accepted  
`max_batch_size` and never handed it to `PipelineModel`, which left the base  
at its default of 1 while the scheduler dispatched full batches. The model  
input buffers a batch stages into are sized from that value, so the first  
multi-context step overran them and the model worker crashed. The  
architectures pass it up now.

Mojo changelog updates:

Raw MAX diff: [https://github.com/modular/modular/compare/579c250800dfde52a4d247fafc53bc048c771cff...26cfe94f400b71afd2cccf439fde95488910c48d](https://github.com/modular/modular/compare/579c250800dfde52a4d247fafc53bc048c771cff...26cfe94f400b71afd2cccf439fde95488910c48d))\>  
Current Mojo changelog: [https://github.com/modular/modular/blob/main/Mojo/docs/site/nightly-changelog.md](https://github.com/modular/modular/blob/main/Mojo/docs/site/nightly-changelog.md)