🔌
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 M4 Max 64GB run DEQ-Transformer (Medium, Adaptive Embedding)?
Yes — here's how fast and up to what context, with real measured numbers.
DEQ-Transformer (Medium, Adaptive Embedding) on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 853k | 1687.6-2035.1 t/s | ~30.9-37.3 (slow) |
| Q8 | yes | 854k | 3375.3-4070.2 t/s | ~61.8-74.5 (slow) |
| Q4 | yes | 855k | 6027.3-7268.2 t/s | ~110.4-133.1 (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 M4 Max 64GB
→ DEQ-Transformer (Medium, Adaptive Embedding) specs
→ Other hardware
FAQ
Can the Apple M4 Max 64GB run DEQ-Transformer (Medium, Adaptive Embedding)?▶
Yes. At Q4 it generates ~6027.3-7268.2 tok/s and fits up to 855k context; beyond that it spills to SSD swap and slows to ~110.4-133.1 tok/s.
How much context fits?▶
At Q4, up to about 855k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.