> I recommend llama.cpp - a direct, open source tool that allows running models on various devices. You don’t need Ollama, and frankly - I would recommend against using that on ethical grounds.
I had faced roadblocks while integrating with openclaw using ollama (Was trying to experiment with `qwen3-vl:2b`). I was tracking the issue back to openclaw at that time, I didn't even consider investigating ollama.
I attached a threads post here where I'm talking to meta ai to expand on both scenarios (not to use ollama, but llama.cpp & my take on the why this is the way it is - ie. commercial gains)
Technologies: PHP, Laravel, NodeJS, TypeScript, ReactJS, NextJS, MySQL, PostgreSQL, MongoDB, AWS, Rust, Inkscape, Gimp, Adobe Suite (Photoshop, Premier Pro, After Effects), Google Analytics, Google Tag Manager,
I'm a freelance software/web/app developer who provides development & designing services. You want a software developed for your SaaS idea or an existing establishment, I'm here for you. Or do you need to rebrand with unique attractive designs to capture the customers attention I'm able to provide that as well.
I'm a software developer (self-taught with ~5+ years of experience) looking to be hired. I have experience working with REST APIs, maintaining backend and frontend development using ReactJS.
Recently I created an article on how to setup a private Stellar blockchain on your system on my blog (decodedhtml[.]com). This was prepared during a hackathon challenge by the Stellar Foundation on dev[.]to platform. I was able to create a dApp and prepare the tutorial, and submitted the same. You find my different projects on my github linked above as where you'll find my CV. You can go through my profile and see my projects. I have spent a lot of time in trying to come up with those architecture. I jumped in to many opensource projects for this, to form an idea on how to build, maintain & scale those projects.
> https://sleepingrobots.com/dreams/stop-using-ollama/
I had faced roadblocks while integrating with openclaw using ollama (Was trying to experiment with `qwen3-vl:2b`). I was tracking the issue back to openclaw at that time, I didn't even consider investigating ollama.
I attached a threads post here where I'm talking to meta ai to expand on both scenarios (not to use ollama, but llama.cpp & my take on the why this is the way it is - ie. commercial gains)
https://www.threads.com/@riojos/post/DaMXIs4k4w8