# Running Pinegrow AI with Locally Installed LLM Ai assistants **URL:** \ **Category:** Questions\ **Created:** [November 28, 2024, 8:14am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042 "2024-11-28T08:14:35Z")\ **Posts on this page:** 12\ **Page:** 2
**Author:** ![reflex](https://avatars.discourse-cdn.com/v4/letter/r/f05b48/32.png) [@reflex](https://forum.pinegrow.com/u/reflex)\ **Post date:** [June 13, 2025, 1:20am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/22 "2025-06-13T01:20:10Z")
I’d like to thank everyone for contributing to this thread. For the most part, I’ve avoided “AI”. A new release of Xcode taps into it, so I started investigating locally hosted models (too cheap to pay subscriptions). Thanks to this thread, (other than an issue I’ve [mentioned here](https://forum.pinegrow.com/t/mr-pine-cone-stuck-on-loading/10815/1)) I was able to get Pinegrow connected to the models of my choice (have gone for devstral as it’s coding orientated) and doing my bidding. ---
**Author:** ![schpengle](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/schpengle/32/238_2.png) [@schpengle](https://forum.pinegrow.com/u/schpengle)\ **Post date:** [June 22, 2025, 10:06am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/23 "2025-06-22T10:06:11Z")
> [@adamslowe](#): > > Also, in case you were wondering, deepseek-r1 is very chatty and Pinegrow doesn’t parse it well at all. Hi there Adam. With regards to the Chatty deepseek thing… this is interesting. [![](https://img.youtube.com/vi/lpWSmKON_go/maxresdefault.jpg "what happens if you give claude's system prompt to llama3...") ](https://www.youtube.com/watch?v=lpWSmKON_go) I didnt realise that… you can create a model, (in this instance using Ollama,) and… change how it behaves! so, you could , following this video example… create a Deepseek R1 model that follows the Claude prompt protocol, which is passed to the model with each request. wow. So bye bye Chatty R1, Hello Claude Style Replies… running on the R1 model. … or… you COULD make it speak _PiRaTe!_ not sure how that would work out for coding but… This video shows how to do it… And its that simple. I might try that later, Tonight. and here is a link to a smaller model of Llama 3.1 …using the Claude Sonnet Prompt which another user has created and uploaded based on this video. > **[incept5/llama3.1-claude](https://ollama.com/incept5/llama3.1-claude:latest)** > > This are Llama3.1 models with Anthropic's Claude Sonnet 3.5 system prompt. Note: Llama model is currently 3.2 and this user created model is 9 months old. Also, the Antrhopic model isnt open source (apparently - correct me if wrong) So creating an updated version of this from 3.1 to the 3.2 instead of this 3.1 older LLM model I was using (not much at all laterly) **should** be easy. Note. The text to be copied for this can be found on the Anthopic site here; > **[System Prompts - Anthropic](https://docs.anthropic.com/en/release-notes/system-prompts#july-12th-2024)** > > See updates to the core system prompts on \[Claude.ai\](https://www.claude.ai) and the Claude \[iOS\](http://anthropic.com/ios) and \[Android\](http://anthropic.com/android) apps. within the \ \ Section So, based on what you experienced… > [@adamslowe](#): > > so far from my very early tests have been [gemma3:12b](https://ollama.com/library/gemma3:12b) and [devstral](https://ollama.com/library/devstral). , if you could find the System prompts used in those 2 models you favour, you could do the same, and create your own _personality_ or _Styled_ model of DeepSeek R1, to see how it delivers code to be parsed by Pinegrow. Challenge accepted? 😃 PS. I just tried Devstral’s own online chat agent to ask about their own System prompt… [https://chat.mistral.ai/chat](https://chat.mistral.ai/chat) … it had no idea… Suspicious! it DID…however have the exact same info for … Claude.. so yeah, maybe dont bother 😃 ![Screenshot 2025-06-22 at 11.30.25](https://canada1.discourse-cdn.com/flex036/uploads/pinegrow/original/2X/9/994b2e2d7881d368b395360d647831b8d264a0a4.jpeg) ---
**Author:** ![adamslowe](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/adamslowe/32/4590_2.png) [@adamslowe](https://forum.pinegrow.com/u/adamslowe)\ **Post date:** [June 24, 2025, 12:58pm UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/24 "2025-06-24T12:58:48Z")
Thanks for the info. There is so much to learn here and my old-man brain is having a hard time keeping up. I do like the idea of coding in pirate-speak, though. Maybe they’ll start embedding some ANSI art like the we saw back in the BBS/Warez days 🤣 ---
**Author:** ![schpengle](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/schpengle/32/238_2.png) [@schpengle](https://forum.pinegrow.com/u/schpengle)\ **Post date:** [June 24, 2025, 8:33pm UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/25 "2025-06-24T20:33:23Z")
![ascii-text-art](https://canada1.discourse-cdn.com/flex036/uploads/pinegrow/original/2X/f/fd3d24b3cc7bc8853329bcb77746be5fb9e0237f.png) ---
**Author:** ![PeteSharp](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/petesharp/32/7134_2.png) [@PeteSharp](https://forum.pinegrow.com/u/PeteSharp)\ **Post date:** [June 25, 2025, 3:31am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/26 "2025-06-25T03:31:43Z")
> [@adamslowe](#): > > ANSI art like the we saw back in the BBS/Warez days Oh that brings back memories. I ran my BBS on an Amiga 500+ and the home phone. We sure must have annoyed people in the household back then. Trying to recall but I think it ran on Max’s BBS software. 🤔. Simpler times. ---
**Author:** ![adamslowe](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/adamslowe/32/4590_2.png) [@adamslowe](https://forum.pinegrow.com/u/adamslowe)\ **Post date:** [June 25, 2025, 11:13am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/27 "2025-06-25T11:13:25Z")
I think it needs more “pirate” 🏴‍☠️ ```auto _ _ _ _ ______ | | ______ __| (_)__| | / __| '_ \| |/ _ \ '_ \ / _` | |/ _` | \__\ |_) | |__/ | | | (_| | | (_| | | ___/ .__ /|_|\ ___|_| |_|\__ ,_|_|\__,_| |_| _ _ _ _____ | |_(_) ______ | '_ \ / _ \| __| |/ _ \| '_ \ | | | | (_) | |_| | (_) | | | | |_| |_|\ ___/ \__ |_|\___/|_| |_| _ _ _____ ___| |____ _ _ | '_ ` _ \ / _` | __/ _ \ | | | | | | | | | (_| | || __/ |_| | |_| |_| |_|\ __,_|\__ \ ___|\__ , | |___/ ``` ---
**Author:** ![adamslowe](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/adamslowe/32/4590_2.png) [@adamslowe](https://forum.pinegrow.com/u/adamslowe)\ **Post date:** [June 25, 2025, 11:15am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/28 "2025-06-25T11:15:36Z")
Oh man, I wish I had an Amiga 500. I used to love using the Amiga Video Toaster machines back in college and always lusted after them. I’m pretty sure my first BBS experience with was Wildcat! Those really were simpler times… ---
**Author:** ![PeteSharp](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/petesharp/32/7134_2.png) [@PeteSharp](https://forum.pinegrow.com/u/PeteSharp)\ **Post date:** [June 26, 2025, 2:58am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/29 "2025-06-26T02:58:11Z")
I miss my Amiga. I also had a 4000 at one stage, wish i has kept it. But i sold it to the animation school i was at, for a line tester. The old days of hand drawn animation. ---
**Author:** ![Zahra](https://avatars.discourse-cdn.com/v4/letter/z/aeb1de/32.png) [@Zahra](https://forum.pinegrow.com/u/Zahra)\ **Post date:** [August 25, 2025, 5:04pm UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/30 "2025-08-25T17:04:24Z")
Good points! LocalAI looks like the most practical way since it mimics the OpenAI API, so PG could potentially connect without much hassle. Modelz LLM is also promising, but I haven’t seen a clear PG integration guide yet. Curious if anyone here has already tested PG with Llama 3 locally? ---
**Author:** ![schpengle](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/schpengle/32/238_2.png) [@schpengle](https://forum.pinegrow.com/u/schpengle)\ **Post date:** [August 27, 2025, 10:04pm UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/31 "2025-08-27T22:04:27Z")
@Zahra Well… yeah. that’s kind of what started this whole thing. here you go 🙂 Its written about here…. > [@Running Pinegrow AI with Locally Installed LLM Ai assistants](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/3): > > Done it! now running Llama 3.2 locally, via Ollama app on the Mac AND …after fumbling around for some time, worked out the API end point and the API key … they are API Key : Ollama End point: [http://localhost:11434/v1/chat/completions](http://localhost:11434/v1/chat/completions) this was after fooling around with the command liine and checking out the text answers etc. I have to admit, im impressed. Really so. But it did then make a few mistakes, like labelling Media queries as a Javascript … unless….._shudders_ you’re some form of bot.. creating random links on here… ---
**Author:** ![chrisb](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/chrisb/32/6761_2.png) [@chrisb](https://forum.pinegrow.com/u/chrisb)\ **Post date:** [September 9, 2025, 3:58am UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/32 "2025-09-09T03:58:20Z")
That was simple, I used Ollama Now need to find a good model to use, any suggestions? ---
**Author:** ![schpengle](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.pinegrow.com/schpengle/32/238_2.png) [@schpengle](https://forum.pinegrow.com/u/schpengle)\ **Post date:** [November 28, 2025, 6:57pm UTC](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042/34 "2025-11-28T18:57:40Z")
Hi @Hame , what you just asked for is written above. self hosted, llm. local machine, on mac. [Previous page](https://forum.pinegrow.com/t/running-pinegrow-ai-with-locally-installed-llm-ai-assistants/10042.md?page=1)