Qwen 3.5 27B is probably the best choice for local, but it will be slow but it's a solid model with much lower memory demands than most.
You are viewing a single comment's thread from:
Qwen 3.5 27B is probably the best choice for local, but it will be slow but it's a solid model with much lower memory demands than most.
and 1M context window
27B is only 262K context window.
80b has 1M :)
Are you talking about Qwen3-Coder-Next 80B? It's only 262K too, but either way these start to get context rot after 100K.
you can enable it to 1M ( but is then slow as fuck). Well and it makes things up. Thats why i think memory files could be the thing to solve it better on infrastructure. But i am still in fuck around find out on that.
using that roping is just absolute garbage
yeah. for now i have https://cline.bot/kanban to explore a bit more before i go into the memory thing again. Since that is cool as fuck too
btw since you are also deeper into it, i experminted with memory files ( like claude) a bit. Any experience with it? So far with stuff like opencode + plugnins like rp1 or others it works well to be always up to date.
Check out mem0
i will do