←back to thread

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

326 points threeturn | 1 comments | 31 Oct 25 13:39 UTC | HN request time: 0.218s | 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. reactordev ◴[31 Oct 25 15:37 UTC] No.45773267[source]▶
I use LM Studio with GGUF models running on either my Apple MacBook Air M1 (it’s, ok…) or my Alienware x17 R2 with an RTX 3080 on a Core i9 (runs like autocomplete) in VS Code using Continue.dev

My only complaint is agent mode needs good token gen so I only go agent mode on the RTX machine.

I grew up on 9600baud so I’m cool with watching the text crawl.