🔌
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 GPT-Neo-2.7B?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-Neo-2.7B on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1213k | 50.4-60.7 t/s | ~1.3-1.5 (slow) |
| Q8 | yes | 1254k | 100.7-121.5 t/s | ~2.5-3 (slow) |
| Q4 | yes | 1272k | 179.9-216.9 t/s | ~4.5-5.4 (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 GPT-Neo-2.7B?▶
Yes. At Q4 it generates ~179.9-216.9 tok/s and fits up to 1272k context; beyond that it spills to SSD swap and slows to ~4.5-5.4 tok/s.
How much context fits?▶
At Q4, up to about 1272k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.