> Reduce your expectations about speed and performance!
Wildly understating this part.
Even the best local models (ones you run on beefy 128GB+ RAM machines) get nowhere close to the sheer intelligence of Claude/Gemini/Codex. At worst these models will move you backwards and just increase the amount of work Claude has to do when your limits reset.
loading story #46893553
The 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.
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.
Which takes a $20k thunderbolt cluster of 2 512GB RAM Mac Studio Ultras to run at full quality…
loading story #46892591
LOCAL models. No one is running Kimi 2.5 on their Macbook or RTX 4090.
Having used K2.5 I’d judge it to be a little better than that. Maybe as good as proprietary models from last June?
loading story #46893046
loading story #46893066
loading story #46892902