# Feature Request: Let Codex Build and Embed Small Task-Specific Local Models

**URL:** <https://community.openai.com/t/feature-request-let-codex-build-and-embed-small-task-specific-local-models/1378578>\
**Category:** Codex\
**Created:** [April 5, 2026, 9:57am UTC](https://community.openai.com/t/feature-request-let-codex-build-and-embed-small-task-specific-local-models/1378578 "2026-04-05T09:57:25Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Curoc1](https://avatars.discourse-cdn.com/v4/letter/c/2acd7d/32.png) [@Curoc1](https://community.openai.com/u/Curoc1)\
**Post date:** [April 5, 2026, 9:57am UTC](https://community.openai.com/t/feature-request-let-codex-build-and-embed-small-task-specific-local-models/1378578/1 "2026-04-05T09:57:25Z")

</div>

Hello OpenAI team,

I would like to request a Codex feature for local-first software development.

Feature idea:  
Allow Codex to optionally prepare, adapt, quantize, and integrate a small task-specific local model into the applications it builds.

Example:  
If I ask Codex to build a debt management desktop app, it should be able to optionally prepare a lightweight local model for that app’s specific use case and integrate it into the generated project so core AI features can work offline.

Why this would be valuable:

- offline and privacy-friendly app experiences
- less dependency on external APIs for end users
- more useful generated apps
- stronger local-first developer workflows
- better support for specialized software

Important note:  
This could be controlled by plan limits or compute limits, so higher tiers could support larger local model workflows while standard paid tiers support smaller task-specific models.

What I’m asking for:

- optional local model preparation inside Codex
- optional task adaptation / lightweight fine-tuning flow
- optional quantization/export flow
- ability to integrate the resulting lightweight model into generated desktop or web apps
- clear controls for model size, runtime limits, and deployment target

This would make Codex much more powerful for developers building real local-first software.

Thanks.

---

<div class="post-metadata">

**Author:** ![OpenAI\_Support](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/openai_support/32/561845_2.png) [@OpenAI\_Support](https://community.openai.com/u/OpenAI_Support)\
**Post date:** [April 9, 2026, 10:01pm UTC](https://community.openai.com/t/feature-request-let-codex-build-and-embed-small-task-specific-local-models/1378578/2 "2026-04-09T22:01:17Z")

</div>

Hey @Curoc1, love the local-first angle. You’re basically proposing a “bundle a lightweight offline model” option in Codex (prep/adapt/quantize + integrate into the project), which would be a big win for offline and privacy-heavy use cases.

I don’t have a timeline to share, but feedback like this is solid signal for where things could improve, and I’ll pass it along internally.

-Sunny