Comment by Pragmata 2 days ago Would this cause issues with SSD lifespan? 5 comments Pragmata Reply vforno 2 days ago What causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter! Pragmata 2 days ago Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different vforno 2 days ago We're working on it right now with a pull request that will also arrive for opencode! Archit3ch 2 days ago You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though. xfalcox 2 days ago README covers thathttps://github.com/JustVugg/colibri#ssd-wear-warning
vforno 2 days ago What causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter! Pragmata 2 days ago Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different vforno 2 days ago We're working on it right now with a pull request that will also arrive for opencode! Archit3ch 2 days ago You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though.
Pragmata 2 days ago Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different vforno 2 days ago We're working on it right now with a pull request that will also arrive for opencode!
vforno 2 days ago We're working on it right now with a pull request that will also arrive for opencode!
Archit3ch 2 days ago You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though.
What causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter!
Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different
We're working on it right now with a pull request that will also arrive for opencode!
You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though.
README covers that
https://github.com/JustVugg/colibri#ssd-wear-warning