🔌
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 64GB run Llama 3.2 11B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama 3.2 11B on the Apple M2 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 213k | 25.7-30.9 t/s | ~0.3-0.4 (slow) |
| Q8 | yes | 278k | 51.3-61.9 t/s | ~0.6-0.8 (slow) |
| Q4 | yes | 306k | 91.6-110.5 t/s | ~1.1-1.4 (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 Ultra 64GB run Llama 3.2 11B?▶
Yes. At Q4 it generates ~91.6-110.5 tok/s and fits up to 306k context; beyond that it spills to SSD swap and slows to ~1.1-1.4 tok/s.
How much context fits?▶
At Q4, up to about 306k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.