🔌
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 ESM2-650M?
Yes — here's how fast and up to what context, with real measured numbers.
ESM2-650M on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 397k | 209.2-252.3 t/s | ~5.2-6.3 (slow) |
| Q8 | yes | 407k | 418.5-504.6 t/s | ~10.5-12.6 (slow) |
| Q4 | yes | 411k | 747.3-901.1 t/s | ~18.7-22.5 (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 ESM2-650M?▶
Yes. At Q4 it generates ~747.3-901.1 tok/s and fits up to 411k context; beyond that it spills to SSD swap and slows to ~18.7-22.5 tok/s.
How much context fits?▶
At Q4, up to about 411k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.