🔌
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 Xinyuan (心元大模型)?
Yes — here's how fast and up to what context, with real measured numbers.
Xinyuan (心元大模型) on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 347k | 9.7-11.7 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 433k | 19.4-23.4 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 470k | 34.7-41.8 t/s | ~0.9-1 (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 Xinyuan (心元大模型)?▶
Yes. At Q4 it generates ~34.7-41.8 tok/s and fits up to 470k context; beyond that it spills to SSD swap and slows to ~0.9-1 tok/s.
How much context fits?▶
At Q4, up to about 470k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.