Model Anatomy See what's inside open-weight AI models

Can I run K2-Horizon-3.7B on a Mac with 16 GB?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 2.85 GB) would fit, with room for ≈ 52K tokens of context. The site hasn't analyzed a GGUF of K2-Horizon-3.7B yet.

Full analysis of K2-Horizon-3.7B Everything that runs on Mac with 16 GB

Files and context on Mac with 16 GB

Each file of K2-Horizon-3.7B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn Mac with 16 GB Context (16-bit)Context (8-bit)
As published10.1 GBDoesn't fit4K7K
4-bit (estimate)2.85 GBFits52K104K

K2-Horizon-3.7B on other hardware

Popular models that run on Mac with 16 GB

Assumes 67% of the Mac's memory is usable (macOS's default limit for the GPU; it can be raised) and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.