🔌
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 Minitron 8B?
Yes — here's how fast and up to what context, with real measured numbers.
Minitron 8B on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 521k | 16.4-19.8 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 584k | 32.8-39.5 t/s | ~0.8-1 (slow) |
| Q4 | yes | 612k | 58.5-70.6 t/s | ~1.5-1.8 (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 M2 Max 96GB run Minitron 8B?▶
Yes. At Q4 it generates ~58.5-70.6 tok/s and fits up to 612k context; beyond that it spills to SSD swap and slows to ~1.5-1.8 tok/s.
How much context fits?▶
At Q4, up to about 612k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.