🔌
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 TiTok-L?
Yes — here's how fast and up to what context, with real measured numbers.
TiTok-L on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 627k | 604.7-729.2 t/s | ~11.1-13.4 (slow) |
| Q8 | yes | 632k | 1209.4-1458.4 t/s | ~22.1-26.7 (slow) |
| Q4 | yes | 634k | 2159.6-2604.2 t/s | ~39.6-47.7 (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 TiTok-L?▶
Yes. At Q4 it generates ~2159.6-2604.2 tok/s and fits up to 634k context; beyond that it spills to SSD swap and slows to ~39.6-47.7 tok/s.
How much context fits?▶
At Q4, up to about 634k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.