🔌
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 AWD-LSTM-DOC (fin) (37M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (37M) on the Apple M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 470k | 2756.8-3324.3 t/s | ~91.9-110.8 (slow) |
| Q8 | yes | 471k | 5513.5-6648.6 t/s | ~183.8-221.6 (slow) |
| Q4 | yes | 471k | 9845.6-11872.6 t/s | ~328.2-395.8 (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 M3 Max 36GB run AWD-LSTM-DOC (fin) (37M)?▶
Yes. At Q4 it generates ~9845.6-11872.6 tok/s and fits up to 471k context; beyond that it spills to SSD swap and slows to ~328.2-395.8 tok/s.
How much context fits?▶
At Q4, up to about 471k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.