# \[TRACKING\] Will the AI Max+ 395 (128GB) be able to run gpt-oss-120b?

**URL:** <https://community.frame.work/t/tracking-will-the-ai-max-395-128gb-be-able-to-run-gpt-oss-120b/73280>\
**Category:** Framework Desktop\
**Tags:** ai, framework-desktop-ai-max-300\
**Created:** [August 5, 2025, 5:22pm UTC](https://community.frame.work/t/tracking-will-the-ai-max-395-128gb-be-able-to-run-gpt-oss-120b/73280 "2025-08-05T17:22:05Z")\
**Posts on this page:** 1\
**Showing post:** 14

<div class="post-metadata">

**Author:** ![geerlingguy](https://sea1.discourse-cdn.com/flex001/user_avatar/community.frame.work/geerlingguy/32/35071_2.png) [@geerlingguy](https://community.frame.work/u/geerlingguy)\
**Post date:** [August 7, 2025, 4:01pm UTC](https://community.frame.work/t/tracking-will-the-ai-max-395-128gb-be-able-to-run-gpt-oss-120b/73280/14 "2025-08-07T16:01:25Z")

</div>

GPT-oss models running under Vulkan: [Benchmark Framework Desktop Mainboard and 4-node cluster · Issue #21 · geerlingguy/ollama-benchmark · GitHub](https://github.com/geerlingguy/ollama-benchmark/issues/21#issuecomment-3164570956)

20b: 45 t/s single node - 97W  
120b: 33 t/s single node - 98W  
120b: 24 t/s clustered (4x) - 138W

---

_[View the full topic](https://community.frame.work/t/tracking-will-the-ai-max-395-128gb-be-able-to-run-gpt-oss-120b/73280)._