Best open models for a Mac with 32 GB
An Apple silicon Mac with 32 GB of unified memory can run language models and vision-language models using MLX or llama.cpp (via LM Studio or Ollama). With roughly 24 GB available for the model after the system and apps, you can run models needing 10–24 GB.
Last updated 3 November 2026 · refreshed after every Hugging Face sync · 15 models
How we rank
Language and vision-language models in MLX or GGUF format whose published weights need about 10–24 GB. We include models seen on Hugging Face in the last 14 days with at least 10,000 downloads in the last 30 days. Score = log10(30-day downloads) + ½ × log10(likes + 1), so popularity leads and likes break near-ties. We keep one entry per model name and leave out adult and uncensored builds. Memory is estimated from parameter count and the published file format (16-bit ≈ 2 bytes per parameter, 4-bit ≈ 0.5) plus 20% headroom; long contexts need more. A quantised copy of a bigger model may also fit — check the model page.