GGUF Quantization Intelligence
Manage LM Studio & GGUF Weights on macOS
LM Studio downloads quantized GGUF models into ~/.cache/lm-studio/models. Over time, multiple quantizations of the same model (e.g. Q4_K_M vs Q8_0) quietly consume over 50 GB.
Locating LM Studio Models on Mac
LM Studio defaults to saving models organized by Hugging Face publisher handles. You can check total size via terminal:
Inspect LM Studio Storage
# Check size of LM Studio models
du -sh ~/.cache/lm-studio/models 2>/dev/null || du -sh ~/.lmstudio/models 2>/dev/null