🔌
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 OpenELM-270M?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-270M on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 408k | 503.7-607.4 t/s | ~12.6-15.2 (slow) |
| Q8 | yes | 412k | 1007.4-1214.8 t/s | ~25.2-30.4 (slow) |
| Q4 | yes | 414k | 1798.9-2169.3 t/s | ~45-54.2 (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 OpenELM-270M?▶
Yes. At Q4 it generates ~1798.9-2169.3 tok/s and fits up to 414k context; beyond that it spills to SSD swap and slows to ~45-54.2 tok/s.
How much context fits?▶
At Q4, up to about 414k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.