🔌
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 Ultra 192GB run Guanaco-65B?
Yes — here's how fast and up to what context, with real measured numbers.
Guanaco-65B on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 126k | 4.2-5 t/s | ~0.1-0.1 (slow) |
| Q8 | yes | 324k | 8.4-10.1 t/s | ~0.1-0.1 (slow) |
| Q4 | yes | 412k | 14.9-18 t/s | ~0.2-0.2 (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 Ultra 192GB run Guanaco-65B?▶
Yes. At Q4 it generates ~14.9-18 tok/s and fits up to 412k context; beyond that it spills to SSD swap and slows to ~0.2-0.2 tok/s.
How much context fits?▶
At Q4, up to about 412k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.