Anyone tried using this as a sub-agent for a more capable model like Claude/Codex?

LatencyKills 2 hours ago | parent | next [-]

The combined (input/output) context window length is 4K. Claude would blow through that even when trying to read and summarize a small file.

▲

khalic an hour ago | parent | prev | next [-]

If you’re looking into small models for tiny local tasks, you should try Qwen coder 0,5B. It’s more of an experiment, but it can output decent functions given the right context instructions.

▲

xenophonf 33 minutes ago | parent [-]

> [Qwen coder 0,5B] can output decent functions given the right context instructions

Can you share a working example?

	▲	khalic 18 minutes ago \| parent [-]
		So… a prompt? I’m not on my laptop but I hooked it to cmp.nvim, gave it a short situational prompt, +- 10 lines, and started typing. Not anywhere near usable but with a little effort you can get something ok for repetitive tasks. Maybe something like spotting one specific code smell pattern. The advantage is the ridiculous T/s you get

▲

franze 2 hours ago | parent | prev [-]

project started with

trying to run openclaw with it in ultra token saving mode, did totally not work.

great for shell scripts though (my major use case now)