🔌
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 M1 Ultra 64GB run OPT-2.7B (finetuned on WT2)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-2.7B (finetuned on WT2) on the Apple M1 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 774k | 100.7-121.5 t/s | ~1.3-1.5 (slow) |
| Q8 | yes | 815k | 201.5-243 t/s | ~2.5-3 (slow) |
| Q4 | yes | 833k | 359.8-433.9 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 M1 Ultra 64GB run OPT-2.7B (finetuned on WT2)?▶
Yes. At Q4 it generates ~359.8-433.9 tok/s and fits up to 833k 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 833k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.