# Download the model file

**URL:** <https://discuss.roboflow.com/t/download-the-model-file/1255>\
**Category:** 🤝  Community Help\
**Tags:** feature-request\
**Created:** [January 9, 2023, 10:01am UTC](https://discuss.roboflow.com/t/download-the-model-file/1255 "2023-01-09T10:01:26Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![joseva\_vacha](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/joseva_vacha/32/1028_2.png) [@joseva\_vacha](https://discuss.roboflow.com/u/joseva_vacha)\
**Post date:** [January 9, 2023, 10:01am UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/1 "2023-01-09T10:01:26Z")

</div>

Can I export/download the model file created after completing the training with the credits?

---

<div class="post-metadata">

**Author:** ![Mohamed](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mohamed/32/62_2.png) [@Mohamed](https://discuss.roboflow.com/u/Mohamed)\
**Post date:** [January 9, 2023, 3:51pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/2 "2023-01-09T15:51:25Z")

</div>

> ℹ **Update (September 2026):** Model weights download is now available on every plan, including the Free Tier, through the [Roboflow Inference](https://inference.roboflow.com) package or the Python SDK. See [Download Roboflow Model Weights](https://docs.roboflow.com/models/model-weights/download-roboflow-model-weights). Self-hosting with Roboflow Inference is also free and doesn’t consume credits. Commercial self-hosting of some models (for example Ultralytics YOLO and RF-DETR 2XL) needs an Enterprise license add-on, see [roboflow.com/licensing](https://roboflow.com/licensing).

* * *

~~Update as of February 2025: our new Basic and Growth plans now include model weights download.~~ Docs: [Download Model Weights | Models | Roboflow Docs](https://docs.roboflow.com/deploy/download-roboflow-model-weights)

> **Old Answer**
>
> Hi @joseva_vacha, for [Roboflow Train](https://docs.roboflow.com/train), we don’t yet provide weights downloads “out of the box.” This has to do, in part, with ensuring all deployments are compatible with your target device(s).
> 
> This is good feedback, however, and something the team is actively considering once scoping out how this would work.
> 
> We do give access to an always-on/always-ready API endpoint; edge device deployment for devices such as iOS and NVIDIA Jetsons; and more deployment options for Enterprise servers and GPU via Docker.
> 
> Everything listed as “On Device” in parentheses here (including all Enterprise options) are available offline, without API.
> 
> - [Serverless Cloud API | Deployment | Roboflow Docs](https://docs.roboflow.com/inference)  
> 
> - Testing local deployment: [Roboflow Inference - Roboflow Inference](https://blog.roboflow.com/locally-deploy-computer-vision/)
> 
> For weights, you would need to train your own model with the [model library](https://roboflow.com/models) (with your own GPU, a cloud-hosted GPU, or hosted GPU notebook such as Google Colab or AWS SageMaker Studio Labs):
> 
> - Full tutorials (written guides and video) for training are available here: [GitHub - roboflow/notebooks: A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. · GitHub](https://github.com/roboflow/notebooks)

---

<div class="post-metadata">

**Author:** ![joseva\_vacha](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/joseva_vacha/32/1028_2.png) [@joseva\_vacha](https://discuss.roboflow.com/u/joseva_vacha)\
**Post date:** [January 11, 2023, 12:36pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/3 "2023-01-11T12:36:58Z")

</div>

Thanks, Mohamed.

- Testing local deployment: [Launch: Test Computer Vision Models Locally](https://blog.roboflow.com/locally-deploy-computer-vision/)

Do we have any limit on the number of times I can use the model for a local deployment? i.e Is there a limit on No. of times I can call model.predict()?

---

<div class="post-metadata">

**Author:** ![Mohamed](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mohamed/32/62_2.png) [@Mohamed](https://discuss.roboflow.com/u/Mohamed)\
**Post date:** [January 11, 2023, 5:14pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/4 "2023-01-11T17:14:54Z")

</div>

> ℹ **Update (September 2026):** Self-hosted inference no longer consumes credits. Running models on your own hardware with [Roboflow Inference](https://inference.roboflow.com) is free on every plan, including the Free Tier. Only Roboflow Cloud deployments (Serverless API, Dedicated Deployments, cloud video streams) use credits. See [roboflow.com/pricing](https://roboflow.com/pricing) for current details.

* * *

_Original answer (January 2023):_

Hi @joseva_vacha, for deployment to devices, there is a device limit of 5 free devices for deployment.

- [Roboflow Pricing: Free, Core & Enterprise Plans](https://roboflow.com/pricing)

These are the posted device limits on the Pricing page for Public workspaces, for example:

 ![image](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/2X/2/2e3f8f0d38d3e5709491b2ee2d93a110fcc0bc77.png)

If you ever receive an error on the device count (i.e the system reading as you’ve deployed to 5 total devices, when you haven’t) please do email us, and I’m happy to get the setting reconfigured.

If you use regular [Hosted API Inference](https://docs.roboflow.com/inference/hosted-api), there are 1,000 free inference credits provided each month for projects in your workspace.

---

<div class="post-metadata">

**Author:** ![Mohamed](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mohamed/32/62_2.png) [@Mohamed](https://discuss.roboflow.com/u/Mohamed)\
**Post date:** [January 11, 2023, 5:17pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/5 "2023-01-11T17:17:54Z")

</div>

Additionally, feel free to Apply for Research Credits, or to become a Blog Contributor, for access to higher device limits without charge: [Contribute to the Computer Vision Community](https://roboflow.com/community)

We’ll get your form reviewed, and set the device limits for your project based on what is approved.

If you are just working on a short-term personal project, we’re also happy to add higher limits for tagging us in a social media post about the project, or including a link to the project in your GitHub repository.

---

<div class="post-metadata">

**Author:** ![HawkingRadiation42](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/hawkingradiation42/32/2009_2.png) [@HawkingRadiation42](https://discuss.roboflow.com/u/HawkingRadiation42)\
**Post date:** [May 25, 2023, 5:27am UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/6 "2023-05-25T05:27:30Z")

</div>

you guys should allow downloading the model weights  
just a feedback

---

<div class="post-metadata">

**Author:** ![Nithishvar\_P](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/nithishvar_p/32/5604_2.png) [@Nithishvar\_P](https://discuss.roboflow.com/u/Nithishvar_P)\
**Post date:** [October 3, 2024, 2:25pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/7 "2024-10-03T14:25:35Z")

</div>

Yes, please consider allowing to download the weights, I have to run in an experimental verdin development board for a startup and I had high hopes for this only to stumble on this blog…

---

<div class="post-metadata">

**Author:** ![brad](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/brad/32/23_2.png) [@brad](https://discuss.roboflow.com/u/brad)\
**Post date:** [February 5, 2025, 6:50pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/8 "2025-02-05T18:50:16Z")

</div>

> ℹ **Update (September 2026):** Model weights download is now available on every plan, including the Free Tier. See the update above for details.

* * *

~~Update as of February 2025: our new Basic and Growth plans now include model weights download.~~ Docs: [Download Model Weights | Models | Roboflow Docs](https://docs.roboflow.com/deploy/download-roboflow-model-weights)

---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/1X/bb6edbfa56d0cf2ee603f061e9e09103502cc8cc.png) [@system](https://discuss.roboflow.com/u/system)\
**Post date:** [February 12, 2025, 6:50pm UTC](https://discuss.roboflow.com/t/download-the-model-file/1255/9 "2025-02-12T18:50:42Z")

</div>

Closed on February 12, 2025, 6:50pm UTC

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.
