🔌
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 UnifiedQA?
Yes — here's how fast and up to what context, with real measured numbers.
UnifiedQA on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 384k | 12.4-14.9 t/s | ~0.3-0.4 (slow) |
| Q8 | yes | 451k | 24.7-29.8 t/s | ~0.6-0.7 (slow) |
| Q4 | yes | 481k | 44.2-53.2 t/s | ~1.1-1.3 (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 M2 Max 96GB run UnifiedQA?▶
Yes. At Q4 it generates ~44.2-53.2 tok/s and fits up to 481k context; beyond that it spills to SSD swap and slows to ~1.1-1.3 tok/s.
How much context fits?▶
At Q4, up to about 481k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.