🔌
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 128GB run ERNIE-Doc (247M)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc (247M) on the Apple M4 Max 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1727k | 751.6-906.3 t/s | ~13.8-16.6 (slow) |
| Q8 | yes | 1731k | 1503.2-1812.6 t/s | ~27.5-33.2 (slow) |
| Q4 | yes | 1733k | 2684.2-3236.8 t/s | ~49.2-59.3 (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 128GB run ERNIE-Doc (247M)?▶
Yes. At Q4 it generates ~2684.2-3236.8 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~49.2-59.3 tok/s.
How much context fits?▶
At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.