🔌
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 M2 Max 32GB run BART-large?
Yes — here's how fast and up to what context, with real measured numbers.
BART-large on the Apple M2 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 404k | 334.7-403.7 t/s | ~8.4-10.1 (slow) |
| Q8 | yes | 410k | 669.5-807.3 t/s | ~16.7-20.2 (slow) |
| Q4 | yes | 413k | 1195.5-1441.6 t/s | ~29.9-36 (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 M2 Max 32GB run BART-large?▶
Yes. At Q4 it generates ~1195.5-1441.6 tok/s and fits up to 413k context; beyond that it spills to SSD swap and slows to ~29.9-36 tok/s.
How much context fits?▶
At Q4, up to about 413k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.