# How to add custom model to chat with rtx?

**URL:** <https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060>\
**Category:** NVIDIA Nemotron\
**Created:** [February 16, 2024, 2:31pm UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060 "2024-02-16T14:31:34Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![aloysiusfaustin](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aloysiusfaustin/32/316335_2.png) [@aloysiusfaustin](https://forums.developer.nvidia.com/u/aloysiusfaustin)\
**Post date:** [February 16, 2024, 2:31pm UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/1 "2024-02-16T14:31:35Z")

</div>

How do I add [  
Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)

to chat with Rtx?

also why when I was installing chat with rtx llama option did not pop up?  
i have the files for it?

---

<div class="post-metadata">

**Author:** ![gue22](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/gue22/32/9995_2.png) [@gue22](https://forums.developer.nvidia.com/u/gue22)\
**Post date:** [February 17, 2024, 8:07pm UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/2 "2024-02-17T20:07:09Z")

</div>

Dunno yet how to add another model, but you seem to have not enough GPU-memory to run Llama-13b, just Mistral-7b, like on my 8GB VRAM 3090 Razer laptop.

Cheers G.

---

<div class="post-metadata">

**Author:** ![aloysiusfaustin](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aloysiusfaustin/32/316335_2.png) [@aloysiusfaustin](https://forums.developer.nvidia.com/u/aloysiusfaustin)\
**Post date:** [February 18, 2024, 1:43am UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/3 "2024-02-18T01:43:01Z")

</div>

Ah I see

---

<div class="post-metadata">

**Author:** ![aloysiusfaustin](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aloysiusfaustin/32/316335_2.png) [@aloysiusfaustin](https://forums.developer.nvidia.com/u/aloysiusfaustin)\
**Post date:** [February 18, 2024, 1:45am UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/4 "2024-02-18T01:45:04Z")

</div>

But I do have 16gb of vram I have a 4070  
Ti it should be able to handle it

---

<div class="post-metadata">

**Author:** ![gue22](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/gue22/32/9995_2.png) [@gue22](https://forums.developer.nvidia.com/u/gue22)\
**Post date:** [February 18, 2024, 7:56am UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/5 "2024-02-18T07:56:45Z")

</div>

thought the 4070 ti only has 12 and the ti super has 16?

---

<div class="post-metadata">

**Author:** ![aloysiusfaustin](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aloysiusfaustin/32/316335_2.png) [@aloysiusfaustin](https://forums.developer.nvidia.com/u/aloysiusfaustin)\
**Post date:** [February 18, 2024, 7:59am UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/6 "2024-02-18T07:59:51Z")

</div>

Oh yeah sorry I meant 12gb

---

<div class="post-metadata">

**Author:** ![antonioaraujo664](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@antonioaraujo664](https://forums.developer.nvidia.com/u/antonioaraujo664)\
**Post date:** [February 23, 2024, 8:35pm UTC](https://forums.developer.nvidia.com/t/how-to-add-custom-model-to-chat-with-rtx/283060/7 "2024-02-23T20:35:52Z")

</div>

I also want to know, I need to add a model that speaks in Portuguese