Can I run QVQ-72B-Preview on a Mac with 64 GB?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 41.3 GB) would fit, with room for ≈ 20K tokens of context. The site hasn't analyzed a GGUF of QVQ-72B-Preview yet.
Files and context on Mac with 64 GB
Each file of QVQ-72B-Preview (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.
| File | Size | On Mac with 64 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 147 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 41.3 GB | Tight | 20K | 40K |