🔌
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 64GB run ESM1b?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1b on the Apple M1 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 836k | 208.5-251.4 t/s | ~5.2-6.3 (slow) |
| Q8 | yes | 846k | 416.9-502.8 t/s | ~10.4-12.6 (slow) |
| Q4 | yes | 850k | 744.5-897.8 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 M1 Max 64GB run ESM1b?▶
Yes. At Q4 it generates ~744.5-897.8 tok/s and fits up to 850k 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 850k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.