🔌
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 48GB run Unicorn?
Yes — here's how fast and up to what context, with real measured numbers.
Unicorn on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 120k | 16.9-20.4 t/s | ~0.3-0.4 (slow) |
| Q8 | yes | 187k | 33.8-40.7 t/s | ~0.6-0.7 (slow) |
| Q4 | yes | 217k | 60.3-72.7 t/s | ~1.1-1.3 (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 48GB run Unicorn?▶
Yes. At Q4 it generates ~60.3-72.7 tok/s and fits up to 217k context; beyond that it spills to SSD swap and slows to ~1.1-1.3 tok/s.
How much context fits?▶
At Q4, up to about 217k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.