🔌
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 64GB run ESM1-670M (UR100)?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1-670M (UR100) on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 836k | 277.4-334.5 t/s | ~5.1-6.1 (slow) |
| Q8 | yes | 846k | 554.8-669 t/s | ~10.2-12.3 (slow) |
| Q4 | yes | 850k | 990.7-1194.7 t/s | ~18.1-21.9 (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 64GB run ESM1-670M (UR100)?▶
Yes. At Q4 it generates ~990.7-1194.7 tok/s and fits up to 850k context; beyond that it spills to SSD swap and slows to ~18.1-21.9 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.