🔌
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 EXAONE Deep 2.4B?
Yes — here's how fast and up to what context, with real measured numbers.
EXAONE Deep 2.4B on the Apple M4 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 398k | 77.4-93.3 t/s | ~1.4-1.7 (slow) |
| Q8 | yes | 435k | 154.7-186.6 t/s | ~2.8-3.4 (slow) |
| Q4 | yes | 451k | 276.3-333.1 t/s | ~5.1-6.1 (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 EXAONE Deep 2.4B?▶
Yes. At Q4 it generates ~276.3-333.1 tok/s and fits up to 451k context; beyond that it spills to SSD swap and slows to ~5.1-6.1 tok/s.
How much context fits?▶
At Q4, up to about 451k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.