# Hoe configureer ik Discourse om een lokaal geïnstalleerde LLM te gebruiken?
**URL:** https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413
**Category:** Support
**Tags:** ai
**Created:** [1 juni 2025 om 11:07 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413 "2025-06-01T11:07:46Z")
**Posts on this page:** 9
**Page:** 1
### Author:  [@meglio](https://meta.discourse.org/u/meglio)
#### Post date: [1 juni 2025 om 11:07 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/1 "2025-06-01T11:07:46Z")
Sorry guys I couldn’t figure out from [this article](https://meta.discourse.org/t/what-llm-to-use-for-discourse-ai/348696/5) if locally installed LLM can be confgirued through the standard settings UI?
---
### Author:  [@mcwumbly](https://meta.discourse.org/u/mcwumbly)
#### Post date: [1 juni 2025 om 11:58 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/2 "2025-06-01T11:58:33Z")
I think as long as it exposes a supported API it should be possible.
Is there a particular LLM you are planning to (or already have) installed locally?
---
### Author:  [@Lilly](https://meta.discourse.org/u/Lilly)
#### Post date: [1 juni 2025 om 12:06 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/3 "2025-06-01T12:06:37Z")
this topic may help
> [@Self-Hosting an OpenSource LLM for DiscourseAI](https://meta.discourse.org/t/self-hosting-an-opensource-llm-for-discourseai/290923):
>
> The [Discourse AI](https://meta.discourse.org/t/discourse-ai/259214) plugin has many features that require an LLM to be enabled, like, for example, Summarization, AI Helper, AI Search, AI Bot. While you can use a third party API, like [Configure API Keys for OpenAI](https://meta.discourse.org/t/configure-api-keys-for-openai/280783) or [Configure API Keys for Anthropic](https://meta.discourse.org/t/configure-api-keys-for-anthropic/280936) we built Discourse AI since first day to not be locked into those. Running with HuggingFace TGI HuggingFace provides an awesome container image that can get you running quickly. For example: mkdir -p /opt/tgi-cache docker run --rm --gpus all --shm…
---
### Author:  [@meglio](https://meta.discourse.org/u/meglio)
#### Post date: [1 juni 2025 om 14:37 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/4 "2025-06-01T14:37:17Z")
> [@mcwumbly](#):
>
> Is there a particular LLM you are planning to (or already have) installed locally?
That’s another exercise to choose the right one - I wasn’t certain even after reading your AI-related articles here at Meta.
I guess some **Open Source LLM Selector** tool from the Discourse Team would be very helpful - because you know the internals and what exactly LLM must be capable of doing for it to excel in various types of tasks relevant to Discourse communities. So, the tool/wizard/LLM would ask questions or let me check on/off in a list of 20+ typical tasks I’d like the LLM to do in my community, and then get a recommended Top 3 ( **uncompromising** but heaviest and requires expensive hardware; **balanced** that requires medium-priced dedicated server; and **lightweight** for basic tasks in small-to-medium communities that can run on a $20-40 VPS).
---
### Author:  [@pfaffman](https://meta.discourse.org/u/pfaffman)
#### Post date: [1 juni 2025 om 15:26 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/5 "2025-06-01T15:26:17Z")
> [@meglio](#):
>
> So, the tool/wizard/LLM would ask questions or let me check on/off in a list of 20+ typical tasks I’d like the LLM to do in my community, and then get a recommended Top 3 ( **uncompromising** but heaviest and requires expensive hardware; **balanced** that requires medium-priced dedicated server; and **lightweight** for basic tasks in small-to-medium communities that can run on a $20-40 VPS).
I think maintaining the correct answer to that would be a full time job. 🤣
---
### Author:  [@sam](https://meta.discourse.org/u/sam)
#### Post date: [2 juni 2025 om 02:21 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/6 "2025-06-02T02:21:52Z")
If you are looking for cheap, Gemini Free tier is the way to go:
> **[Gemini Developer API pricing | Gemini API | Google AI for Developers](https://ai.google.dev/gemini-api/docs/pricing)**
>
> Gemini Developer API Pricing
Gemini flash 2.0 is a very capable model and the free tier provides enough usage to perform quite a few things on your forum.
---
### Author:  [@meglio](https://meta.discourse.org/u/meglio)
#### Post date: [2 juni 2025 om 03:48 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/7 "2025-06-02T03:48:57Z")
Looking for locally hosted because I can’t send any of our content to any service outside our servers.
Re cheap options, thanks for the hint!
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [3 juni 2025 om 15:59 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/8 "2025-06-03T15:59:43Z")
> [@meglio](#):
>
> a recommended Top 3 ( **uncompromising** but heaviest and requires expensive hardware; **balanced** that requires medium-priced dedicated server; and **lightweight** for basic tasks in small-to-medium communities that can run on a $20-40 VPS).
### Uncompromising
- DeepSeek V3 0324
- Qwen 3 235B A22
### Balanced
- Qwen 3 32B / 30B A3B
- Llama 3.3 70B
- Qwen 2.5 70B
### Lightweight
Maybe [unsloth/gemma-3-4b-it-qat-GGUF · Hugging Face](https://huggingface.co/unsloth/gemma-3-4b-it-qat-GGUF) ? It’s hard at this level, much more economical to use a hosted API, like OpenRouter.
---
### Author:  [@tobiaseigen](https://meta.discourse.org/u/tobiaseigen)
#### Post date: [17 september 2025 om 20:40 UTC](https://meta.discourse.org/t/how-to-configure-discourse-to-use-a-locally-installed-llm/368413/9 "2025-09-17T20:40:15Z")