logoalt Hacker News

slowinyesterday at 5:37 PM3 repliesview on HN

Just to be clear, I'm specifically talking about coding. I think local models can help with productivity today, just not coding.

I'm also a huge fan of local models and think it's absolutely imperative that they continue to advance so we can move off of the Anthropic/OpenAI hosted models. It's important to accurately asses where we are in that journey though.


Replies

srcreighyesterday at 5:41 PM

I think the issue is generalization, if you were more specific about which local models aren’t good enough for which tasks compared to which frontier models in your experience, it’d be a lot more informative

show 1 reply
_hugerobots_yesterday at 6:14 PM

Like the other commenter, I'm confused about the 'just not coding' conclusion. I'm using Qwen 27B on a 5090 at > 100tk/s with 150k context (which isn't enough admittedly), and DeepSeek v4 Flash with 1million context on a gb10/spark. Both of which are performing surface level, and deep needle precision infrastructure architecture. They code 24-7, stupendously.

show 1 reply
brandon272yesterday at 9:44 PM

Local models are undeniably capable of "helping with coding" today.

show 1 reply