🔌
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 M1 Ultra 64GB run ERNIE-4.5-0.3B?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-4.5-0.3B on the Apple M1 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 845k | 755.6-911.1 t/s | ~9.4-11.4 (slow) |
| Q8 | yes | 851k | 1511.1-1822.2 t/s | ~18.9-22.8 (slow) |
| Q4 | yes | 853k | 2698.4-3254 t/s | ~33.7-40.7 (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 M1 Ultra 64GB run ERNIE-4.5-0.3B?▶
Yes. At Q4 it generates ~2698.4-3254 tok/s and fits up to 853k context; beyond that it spills to SSD swap and slows to ~33.7-40.7 tok/s.
How much context fits?▶
At Q4, up to about 853k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.