🔌
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 M2 Max 32GB run Sailor-7B-Chat?
Yes — here's how fast and up to what context, with real measured numbers.
Sailor-7B-Chat on the Apple M2 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 90k | 17.6-21.2 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 149k | 35.2-42.5 t/s | ~0.9-1.1 (slow) |
| Q4 | yes | 175k | 62.9-75.9 t/s | ~1.6-1.9 (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 M2 Max 32GB run Sailor-7B-Chat?▶
Yes. At Q4 it generates ~62.9-75.9 tok/s and fits up to 175k context; beyond that it spills to SSD swap and slows to ~1.6-1.9 tok/s.
How much context fits?▶
At Q4, up to about 175k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.