🔌
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 36GB run Falcon Perception?
Yes — here's how fast and up to what context, with real measured numbers.
Falcon Perception on the Apple M4 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 453k | 309.4-373.1 t/s | ~5.7-6.8 (slow) |
| Q8 | yes | 462k | 618.8-746.2 t/s | ~11.3-13.7 (slow) |
| Q4 | yes | 466k | 1105-1332.5 t/s | ~20.2-24.4 (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 M4 Max 36GB run Falcon Perception?▶
Yes. At Q4 it generates ~1105-1332.5 tok/s and fits up to 466k context; beyond that it spills to SSD swap and slows to ~20.2-24.4 tok/s.
How much context fits?▶
At Q4, up to about 466k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.