🔌
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 M4 Max 64GB run TurboVLA?
Yes — here's how fast and up to what context, with real measured numbers.
TurboVLA on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 850k | 928.2-1119.3 t/s | ~17-20.5 (slow) |
| Q8 | yes | 853k | 1856.4-2238.6 t/s | ~34-41 (slow) |
| Q4 | yes | 854k | 3315-3997.5 t/s | ~60.7-73.2 (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 M4 Max 64GB run TurboVLA?▶
Yes. At Q4 it generates ~3315-3997.5 tok/s and fits up to 854k context; beyond that it spills to SSD swap and slows to ~60.7-73.2 tok/s.
How much context fits?▶
At Q4, up to about 854k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.