🔌
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 M1 Max 32GB run CARP?
Yes — here's how fast and up to what context, with real measured numbers.
CARP on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 397k | 211.5-255.1 t/s | ~5.3-6.4 (slow) |
| Q8 | yes | 407k | 423-510.1 t/s | ~10.6-12.8 (slow) |
| Q4 | yes | 411k | 755.4-910.9 t/s | ~18.9-22.8 (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 M1 Max 32GB run CARP?▶
Yes. At Q4 it generates ~755.4-910.9 tok/s and fits up to 411k context; beyond that it spills to SSD swap and slows to ~18.9-22.8 tok/s.
How much context fits?▶
At Q4, up to about 411k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.