alt Hacker NewsThe best open models such as Kimi 2.5 are about as smart today as the big proprietary models were one year ago. That's not "nothing" and is plenty good enough for everyday work.
Replies
corysama • yesterday at 11:38 PM
The article mentions https://unsloth.ai/docs/basics/claude-codex
I'll add on https://unsloth.ai/docs/models/qwen3-coder-next
The full model is supposedly comparable to Sonnet 4.5 But, you can run the 4 bit quant on consumer hardware as long as your RAM + VRAM has room to hold 46GB. 8 bit needs 85.
paxys • yesterday at 10:24 PM
LOCAL models. No one is running Kimi 2.5 on their Macbook or RTX 4090.
teaearlgraycold • yesterday at 10:12 PM
Having used K2.5 I’d judge it to be a little better than that. Maybe as good as proprietary models from last June?
Which takes a $20k thunderbolt cluster of 2 512GB RAM Mac Studio Ultras to run at full quality…