Setting up OpenCode with Ollama and sbx on Mac

Posted by etoxin 2 days ago

Comments

Comment by manapause 2 days ago

If you have both ollama and llama.cpp installed on your MBP, and are interested in utilizing your local model as a cost-saving preprocessor for your frontier models, consider using https://github.com/Standard-Pentest/kultivait!

"kultivait init --setup" to evaluate your machine's hardware, access to frontier cli-tools, download models, and create a proxy for ollama to get started. works great with opencode!

Comment by manapause 1 day ago

Note: I am replying to my own post to say that Kultivait llama.cpp functionality is currently broken but under active development.

Ollama proxy and model selection does work. If you run into issues or have any questions please feel free to reach out.

Comment by hkchad 2 days ago

Friends don't let friends use Ollama

Comment by yonatan8070 1 day ago

Can you elaborate for your unaware Ollama-using friends?

Comment by matusnovak 1 day ago

What the parent comment is referencing: https://sleepingrobots.com/dreams/stop-using-ollama/

Comment by darthcircuit 2 days ago

I’ve been using OMLX on 48gb Mac. It’s a lot smoother setup than Ollama and has a built in model sizer and all that in a nice ui. Also will pre configure and launch opencode, pi, Hermes, codex and Claude out of the box with no fuss. I’ve been really happy with it.

Comment by etoxin 1 day ago

I did try oMLX, mlx and LM studio (Now Bionic). I returned back to Ollama because of stability issues.

Comment by slimelephantjbx 1 day ago

Ollama is the best for backends, I prefer using LM mini as a UI though, cause it lets me sync chats between my phone and mac.

Comment by cube00 2 days ago

>Why I use Ollama. To be frank it's just easy.

More ethical alternatives have caught up including llama.cpp

https://sleepingrobots.com/dreams/stop-using-ollama/#what-to...

Comment by LoganDark 2 days ago

Very ironic how that article looks like it was LLM generated.

Comment by reaperducer 2 days ago

Dogfooding it!

Comment by LoganDark 2 days ago

At least it looks like the quality control wasn't too bad!

Comment by vivzkestrel 1 day ago

- Stop using OLLAMA

- https://sleepingrobots.com/dreams/stop-using-ollama/

- also can we get a post on how to do this with llama.cpp

Comment by villgax 2 days ago

Lol why bother with bloat ollama

Comment by hefu_hk 2 days ago

[flagged]

Comment by slimelephant 1 day ago

[flagged]