[heelix]

One of the double edge swords I see is devs/evangelists pushing agentic coding are playing the 'good enough' statement. If that is true and those asking for software can live with good enough AI code, the moment the free local models hit that level the party is over in the continual push to the premium tip of the spear models.

[neutrinobro]

We might already be there. I've been running Qwen-3.6-27B with 8-bit quantization locally with llama.cpp (~100k context window), and to be honest for my use case, 40-50% of the time it is more usable than claude-code. I only have the $20/mo plan, so I often hit rate limits after 2-3 prompts. And while the local model is slower, it just keeps chugging, is practically free, and more often than not produces code similar to claude. I wouldn't be surprised if in 6-12 months we have local models which are comparable to opus 4.6...which I personally consider as a tipping point where agentic coding became practical.