🔌
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 EXAONE 3.0?
Yes — here's how fast and up to what context, with real measured numbers.
EXAONE 3.0 on the Apple M4 Max 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 748k | 23.7-28.6 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 808k | 47.5-57.3 t/s | ~0.9-1 (slow) |
| Q4 | yes | 834k | 84.8-102.2 t/s | ~1.6-1.9 (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 EXAONE 3.0?▶
Yes. At Q4 it generates ~84.8-102.2 tok/s and fits up to 834k context; beyond that it spills to SSD swap and slows to ~1.6-1.9 tok/s.
How much context fits?▶
At Q4, up to about 834k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.