🔌
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-NeXT-34B (LLaVA-1.6)?
Yes — here's how fast and up to what context, with real measured numbers.
LLaVA-NeXT-34B (LLaVA-1.6) on the Apple M2 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | no | — | — | — |
| Q8 | yes | 81k | 15.7-18.9 t/s | ~0.2-0.2 (slow) |
| Q4 | yes | 140k | 28-33.7 t/s | ~0.3-0.4 (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 LLaVA-NeXT-34B (LLaVA-1.6)?▶
Yes. At Q4 it generates ~28-33.7 tok/s and fits up to 140k context; beyond that it spills to SSD swap and slows to ~0.3-0.4 tok/s.
How much context fits?▶
At Q4, up to about 140k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.