🔌
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 M3 Max 36GB run Hyena-2 153M?
Yes — here's how fast and up to what context, with real measured numbers.
Hyena-2 153M on the Apple M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 467k | 666.7-803.9 t/s | ~22.2-26.8 (slow) |
| Q8 | yes | 469k | 1333.3-1607.8 t/s | ~44.4-53.6 (slow) |
| Q4 | yes | 470k | 2381-2871.1 t/s | ~79.4-95.7 (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 M3 Max 36GB run Hyena-2 153M?▶
Yes. At Q4 it generates ~2381-2871.1 tok/s and fits up to 470k context; beyond that it spills to SSD swap and slows to ~79.4-95.7 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.