🔌
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 96GB 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 M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1292k | 1236.4-1490.9 t/s | ~30.9-37.3 (slow) |
| Q8 | yes | 1294k | 2472.7-2981.8 t/s | ~61.8-74.5 (slow) |
| Q4 | yes | 1295k | 4415.6-5324.7 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 M2 Max 96GB
→ DEQ-Transformer (Medium, Adaptive Embedding) specs
→ Other hardware
FAQ
Can the Apple M2 Max 96GB run DEQ-Transformer (Medium, Adaptive Embedding)?▶
Yes. At Q4 it generates ~4415.6-5324.7 tok/s and fits up to 1295k 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 1295k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.