🔌
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 KeTu (Kolors)?
Yes — here's how fast and up to what context, with real measured numbers.
KeTu (Kolors) on the Apple M4 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 392k | 71.4-86.1 t/s | ~1.3-1.6 (slow) |
| Q8 | yes | 432k | 142.8-172.2 t/s | ~2.6-3.2 (slow) |
| Q4 | yes | 449k | 255-307.5 t/s | ~4.7-5.6 (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 KeTu (Kolors)?▶
Yes. At Q4 it generates ~255-307.5 tok/s and fits up to 449k context; beyond that it spills to SSD swap and slows to ~4.7-5.6 tok/s.
How much context fits?▶
At Q4, up to about 449k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.