🔌
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 64GB run ULM-FiT?
Yes — here's how fast and up to what context, with real measured numbers.
ULM-FiT on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 843k | 421-507.6 t/s | ~7.7-9.3 (slow) |
| Q8 | yes | 849k | 841.9-1015.2 t/s | ~15.4-18.6 (slow) |
| Q4 | yes | 852k | 1503.4-1812.9 t/s | ~27.5-33.2 (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 64GB run ULM-FiT?▶
Yes. At Q4 it generates ~1503.4-1812.9 tok/s and fits up to 852k context; beyond that it spills to SSD swap and slows to ~27.5-33.2 tok/s.
How much context fits?▶
At Q4, up to about 852k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.