🔌
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 Max 96GB run TurboVLA?
Yes — here's how fast and up to what context, with real measured numbers.
TurboVLA on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1289k | 680-820 t/s | ~17-20.5 (slow) |
| Q8 | yes | 1292k | 1360-1640 t/s | ~34-41 (slow) |
| Q4 | yes | 1294k | 2428.6-2928.6 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 M2 Max 96GB run TurboVLA?▶
Yes. At Q4 it generates ~2428.6-2928.6 tok/s and fits up to 1294k 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 1294k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.