🔌
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 ESM1-43M?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1-43M on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 635k | 4357.7-5254.9 t/s | ~79.8-96.2 (slow) |
| Q8 | yes | 636k | 8715.5-10509.9 t/s | ~159.6-192.5 (slow) |
| Q4 | yes | 636k | 15563.4-18767.6 t/s | ~285-343.7 (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 M4 Max 48GB run ESM1-43M?▶
Yes. At Q4 it generates ~15563.4-18767.6 tok/s and fits up to 636k context; beyond that it spills to SSD swap and slows to ~285-343.7 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.