🔌
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 192GB run S4?
Yes — here's how fast and up to what context, with real measured numbers.
S4 on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2606k | 1092.4-1317.3 t/s | ~13.7-16.5 (slow) |
| Q8 | yes | 2610k | 2184.7-2634.5 t/s | ~27.3-32.9 (slow) |
| Q4 | yes | 2612k | 3901.3-4704.5 t/s | ~48.8-58.8 (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 192GB run S4?▶
Yes. At Q4 it generates ~3901.3-4704.5 tok/s and fits up to 2612k context; beyond that it spills to SSD swap and slows to ~48.8-58.8 tok/s.
How much context fits?▶
At Q4, up to about 2612k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.