🔌
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 Max 32GB run HyenaDNA?
Yes — here's how fast and up to what context, with real measured numbers.
HyenaDNA on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 416k | 20606.1-24848.5 t/s | ~515.2-621.2 (slow) |
| Q8 | yes | 416k | 41212.1-49697 t/s | ~1030.3-1242.4 (slow) |
| Q4 | yes | 417k | 73593.1-88744.6 t/s | ~1839.8-2218.6 (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 Max 32GB run HyenaDNA?▶
Yes. At Q4 it generates ~73593.1-88744.6 tok/s and fits up to 417k context; beyond that it spills to SSD swap and slows to ~1839.8-2218.6 tok/s.
How much context fits?▶
At Q4, up to about 417k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.