🔌
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 LLaVA-OV-7B?
Yes — here's how fast and up to what context, with real measured numbers.
LLaVA-OV-7B on the Apple M2 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 312k | 35.8-43.2 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 370k | 71.6-86.3 t/s | ~0.9-1.1 (slow) |
| Q4 | yes | 396k | 127.8-154.1 t/s | ~1.6-1.9 (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 LLaVA-OV-7B?▶
Yes. At Q4 it generates ~127.8-154.1 tok/s and fits up to 396k context; beyond that it spills to SSD swap and slows to ~1.6-1.9 tok/s.
How much context fits?▶
At Q4, up to about 396k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.