Hacker News Reader

I'm told that qwen 3.8 27B is good enough for practical programming work, so if that's doable then I could easily see the utility. Or... the biggest qwen I see here is Qwen3.5-2B; is that actually capable of programming or agentic work with code?

View on HN

It's not, but tiny models have so far been on the same track of increasing capabilities as large ones. The parameters needed to do useful work keeps going down. It hasn't reached 2B yet, but it's very possible it'll get there. In the last month we've gotten 4B models that can do small tasks.

> In the last month we've gotten 4B models that can do small tasks.

where can I read up on that?

Check LFM as a starting pointer : https://www.liquid.ai/models

The best one I know of at the moment is XHToken's Spark-x2.6 4B.

Reply on news.ycombinator.com