Hacker News Reader

Yeah, but that's personal use at best, not much agentic anything happening on that hardware. Macs are great for small models at small-medium context lengths, but at > 64k (something very common with agentic usage) it struggles and slows down a lot.

The ~100k hardware is suitable for multi-user, small team usage. That's what you'd use for actual work in reasonable timeframes. For personal use, sure macs could work.

True, but I think for local models, we are mostly considering personal usage.

You could run it with SSD offload, earlier experiments with Kimi 2.5 on M5 hardware had it running at 2 tok/s. K2.6 has a similar amount of total and active parameters.

Yeah... I would definitely call 2t/s unusable. For simple chats, I'd want at least 15 t/s. For agentic coding (which this model is advertised for), I'd want good prefill performance as well.

That's just throwing money away. The performance with large context would have been unusable especially if you need to serve more then a single person.