🔌
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 Stable Diffusion (LDM-KL-8-G)?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Diffusion (LDM-KL-8-G) on the Apple M2 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 372k | 93.8-113.1 t/s | ~2.3-2.8 (slow) |
| Q8 | yes | 394k | 187.6-226.2 t/s | ~4.7-5.7 (slow) |
| Q4 | yes | 404k | 335-403.9 t/s | ~8.4-10.1 (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 M2 Max 32GB run Stable Diffusion (LDM-KL-8-G)?▶
Yes. At Q4 it generates ~335-403.9 tok/s and fits up to 404k context; beyond that it spills to SSD swap and slows to ~8.4-10.1 tok/s.
How much context fits?▶
At Q4, up to about 404k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.