326 points threeturn | 1 comments | 31 Oct 25 13:39 UTC | HN request time: 0.198s | source

Dear Hackers, I’m interested in your real-world workflows for using open-source LLMs and open-source coding assistants on your laptop (not just cloud/enterprise SaaS). Specifically:

Which model(s) are you running (e.g., Ollama, LM Studio, or others) and which open-source coding assistant/integration (for example, a VS Code plugin) you’re using?

What laptop hardware do you have (CPU, GPU/NPU, memory, whether discrete GPU or integrated, OS) and how it performs for your workflow?

What kinds of tasks you use it for (code completion, refactoring, debugging, code review) and how reliable it is (what works well / where it falls short).

I'm conducting my own investigation, which I will be happy to share as well when over.

Thanks! Andrea.

1. alexfromapex ◴[31 Oct 25 17:46 UTC] No.45774690[source]▶

>>45771870 (OP) #

I have a MacBook M3 Max with 128 GB unified RAM. I use Ollama with Open Web UI. It performs very well with models up to 80B parameters but it does get very hot with models over 20B parameters.

I use it to do simple text-based tasks occasionally if my Internet is down or ChatGPT is down.

I also use it in VS Code to help with code completion using the Continue extension.

I created a Firefox extension so I can use Open WebUI in my browser by pressing Cmd+Shift+Space too when I am browsing the web and want to ask a question: https://addons.mozilla.org/en-US/firefox/addon/foxyai/

↑

Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop