🔌
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 96GB run ProGen2-base?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-base on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1272k | 178-214.7 t/s | ~4.5-5.4 (slow) |
| Q8 | yes | 1284k | 356-429.3 t/s | ~8.9-10.7 (slow) |
| Q4 | yes | 1289k | 635.8-766.6 t/s | ~15.9-19.2 (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 96GB run ProGen2-base?▶
Yes. At Q4 it generates ~635.8-766.6 tok/s and fits up to 1289k context; beyond that it spills to SSD swap and slows to ~15.9-19.2 tok/s.
How much context fits?▶
At Q4, up to about 1289k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.