News for hackers. Stuff that matters.

A comment on GitHub Copilot is moving to usage-based billing.

Re:GitHub Copilot is moving to usage-based billing by jareds on Monday April 27, 2026 @02:07PM (#47925100)
What's the current situation for coding with Local LLM's on decent hardware? I have an M3 Max with 64 gb of ram and am thinking I should start looking at Ollama and Opencode? Is this a useful stack for smaller personal projects?
[ Parent | on HN ]
Re:GitHub Copilot is moving to usage-based billing by speedgoose on Monday April 27, 2026 @03:53PM (#47926478)
It’s getting there. You could give a try with qwen 3.6. It’s worth paying for better models in the cloud, but local models are now better than nothing.
[ Parent | on HN ]
Re:GitHub Copilot is moving to usage-based billing by pohl on Monday April 27, 2026 @02:33PM (#47925417)
One nice development recently was ollama's support for MLX optimization on Mac hardware. It's not obvious how to know you're using a model that works with it, yet, so it's rough around the edges.

https://ollama.com/blog/mlx

[ Parent | on HN ]
Re:GitHub Copilot is moving to usage-based billing by satvikpendem on Monday April 27, 2026 @04:43PM (#47927061)
Use llama.cpp or better yet Unsloth Studio
[ Parent | on HN ]