🔌
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 CLIP (ResNet-50)?
Yes — here's how fast and up to what context, with real measured numbers.
CLIP (ResNet-50) on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 414k | 1535-1851 t/s | ~38.4-46.3 (slow) |
| Q8 | yes | 415k | 3070-3702 t/s | ~76.7-92.6 (slow) |
| Q4 | yes | 416k | 5482.1-6610.8 t/s | ~137.1-165.3 (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 CLIP (ResNet-50)?▶
Yes. At Q4 it generates ~5482.1-6610.8 tok/s and fits up to 416k context; beyond that it spills to SSD swap and slows to ~137.1-165.3 tok/s.
How much context fits?▶
At Q4, up to about 416k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.