🔌
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 Minerva 7B?
Yes — here's how fast and up to what context, with real measured numbers.
Minerva 7B on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 535k | 18.4-22.2 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 591k | 36.8-44.3 t/s | ~0.9-1.1 (slow) |
| Q4 | yes | 616k | 65.6-79.2 t/s | ~1.6-2 (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 Minerva 7B?▶
Yes. At Q4 it generates ~65.6-79.2 tok/s and fits up to 616k context; beyond that it spills to SSD swap and slows to ~1.6-2 tok/s.
How much context fits?▶
At Q4, up to about 616k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.