🔌
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 ERNIE-Doc Base (151M, WT103)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc Base (151M, WT103) on the Apple M4 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 467k | 1229.4-1482.5 t/s | ~22.5-27.2 (slow) |
| Q8 | yes | 469k | 2458.8-2965 t/s | ~45-54.3 (slow) |
| Q4 | yes | 470k | 4390.7-5294.7 t/s | ~80.4-97 (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 ERNIE-Doc Base (151M, WT103)?▶
Yes. At Q4 it generates ~4390.7-5294.7 tok/s and fits up to 470k context; beyond that it spills to SSD swap and slows to ~80.4-97 tok/s.
How much context fits?▶
At Q4, up to about 470k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.