🔌
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 Ultra 64GB run BLOOM-1.7B?
Yes — here's how fast and up to what context, with real measured numbers.
BLOOM-1.7B on the Apple M2 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 804k | 160-192.9 t/s | ~2-2.4 (slow) |
| Q8 | yes | 830k | 320-385.9 t/s | ~4-4.8 (slow) |
| Q4 | yes | 841k | 571.4-689.1 t/s | ~7.1-8.6 (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 Ultra 64GB run BLOOM-1.7B?▶
Yes. At Q4 it generates ~571.4-689.1 tok/s and fits up to 841k context; beyond that it spills to SSD swap and slows to ~7.1-8.6 tok/s.
How much context fits?▶
At Q4, up to about 841k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.