←back to thread

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

326 points threeturn | 8 comments | 31 Oct 25 13:39 UTC | HN request time: 1.224s | source | bottom

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. gcr ◴[31 Oct 25 20:11 UTC] No.45776181[source]▶
For new folks, you can get a local code agent running on your Mac like this:

1. $ npm install -g @openai/codex

2. $ brew install ollama; ollama serve

3. $ ollama pull gpt-oss:20b

4. $ codex --oss -m gpt-oss:20b

This runs locally without Internet. Idk if there’s telemetry for codex, but you should be able to turn that off if so.

You need an M1 Mac or better with at least 24GB of GPU memory. The model is pretty big, about 16GB of disk space in ~/.ollama

Be careful - the 120b model is 1.5× better than this 20b variant, but takes 5× higher requirements.

replies(4): >>45776470 #>>45778342 #>>45778839 #>>45779085 #
2. nickthegreek ◴[31 Oct 25 20:41 UTC] No.45776470[source]▶
have you been able to build or reiterate anything of value using just 20b to vibe code?
3. giancarlostoro ◴[01 Nov 25 00:57 UTC] No.45778342[source]▶
LM Studio is even easier, and things like JetBrains IDEs will sync to LM Studio, same with Zed.
4. abacadaba ◴[01 Nov 25 02:41 UTC] No.45778839[source]▶
As much as I've been using llms via api all day every day, being able to run it locally on my mba and talk to my laptop still feels like magic
5. windexh8er ◴[01 Nov 25 03:42 UTC] No.45779085[source]▶
I've been really impressed by OpenCode [0]. The limitations of all the frontier TUI is removed and it is feature complete and performant compared to Codex or Claude Code.

[0] https://opencode.ai/

replies(1): >>45781286 #
6. embedding-shape ◴[01 Nov 25 12:57 UTC] No.45781286[source]▶
> OpenCode will be available on desktop soon

Anyone happen to know what that means exactly? The install instructions at the top seems to indicate it already is available on desktop?

replies(1): >>45783168 #
7. windexh8er ◴[01 Nov 25 16:50 UTC] No.45783168{3}[source]▶
It's a terminal only (TUI) tool today. They're releasing a graphical (GUI) version in the future.
replies(1): >>45783234 #
8. embedding-shape ◴[01 Nov 25 16:57 UTC] No.45783234{4}[source]▶
> It's a terminal only (TUI) tool today.

But to use that TUI you need a desktop, or at least a laptop I guess, but that distinction doesn't make sense. Are they referring to the GUI being the "Desktop Version"? Never heard it put that way before if so.