🔌
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 M3 Max 36GB run BLOOM-560M?
Yes — here's how fast and up to what context, with real measured numbers.
BLOOM-560M on the Apple M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 454k | 182.1-219.6 t/s | ~6.1-7.3 (slow) |
| Q8 | yes | 463k | 364.3-439.3 t/s | ~12.1-14.6 (slow) |
| Q4 | yes | 467k | 650.5-784.4 t/s | ~21.7-26.1 (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 M3 Max 36GB run BLOOM-560M?▶
Yes. At Q4 it generates ~650.5-784.4 tok/s and fits up to 467k context; beyond that it spills to SSD swap and slows to ~21.7-26.1 tok/s.
How much context fits?▶
At Q4, up to about 467k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.