🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Apple M4 Max 48GB run DARTS (second order) (PTB)?
Yes — here's how fast and up to what context, with real measured numbers.
DARTS (second order) (PTB) on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 636k | 8071.3-9733 t/s | ~147.8-178.3 (slow) |
| Q8 | yes | 636k | 16142.6-19466.1 t/s | ~295.7-356.5 (slow) |
| Q4 | yes | 636k | 28826.1-34760.9 t/s | ~528-636.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the Apple M4 Max 48GB run DARTS (second order) (PTB)?▶
Yes. At Q4 it generates ~28826.1-34760.9 tok/s and fits up to 636k context; beyond that it spills to SSD swap and slows to ~528-636.6 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.