🔌
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 LFM2.5-ColBERT-350M?
Yes — here's how fast and up to what context, with real measured numbers.
LFM2.5-ColBERT-350M on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 406k | 388.6-468.6 t/s | ~9.7-11.7 (slow) |
| Q8 | yes | 411k | 777.1-937.1 t/s | ~19.4-23.4 (slow) |
| Q4 | yes | 414k | 1387.8-1673.5 t/s | ~34.7-41.8 (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 LFM2.5-ColBERT-350M?▶
Yes. At Q4 it generates ~1387.8-1673.5 tok/s and fits up to 414k context; beyond that it spills to SSD swap and slows to ~34.7-41.8 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.