🔌
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 48GB run ESM1b?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1b on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 616k | 284.5-343.1 t/s | ~5.2-6.3 (slow) |
| Q8 | yes | 626k | 569.1-686.3 t/s | ~10.4-12.6 (slow) |
| Q4 | yes | 631k | 1016.2-1225.5 t/s | ~18.6-22.4 (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 48GB run ESM1b?▶
Yes. At Q4 it generates ~1016.2-1225.5 tok/s and fits up to 631k context; beyond that it spills to SSD swap and slows to ~18.6-22.4 tok/s.
How much context fits?▶
At Q4, up to about 631k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.