🔌
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 64GB run AWD-LSTM-DRILL + dynamic evaluation† (WT2)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DRILL + dynamic evaluation† (WT2) on the Apple M3 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 855k | 4000-4823.5 t/s | ~100-120.6 (slow) |
| Q8 | yes | 855k | 8000-9647.1 t/s | ~200-241.2 (slow) |
| Q4 | yes | 856k | 14285.7-17226.9 t/s | ~357.1-430.7 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the Apple M3 Max 64GB
→ AWD-LSTM-DRILL + dynamic evaluation† (WT2) specs
→ Other hardware
FAQ
Can the Apple M3 Max 64GB run AWD-LSTM-DRILL + dynamic evaluation† (WT2)?▶
Yes. At Q4 it generates ~14285.7-17226.9 tok/s and fits up to 856k context; beyond that it spills to SSD swap and slows to ~357.1-430.7 tok/s.
How much context fits?▶
At Q4, up to about 856k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.