🔌
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 Theseus 6/768?
Yes — here's how fast and up to what context, with real measured numbers.
Theseus 6/768 on the Apple M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 469k | 1545.5-1863.6 t/s | ~51.5-62.1 (slow) |
| Q8 | yes | 470k | 3090.9-3727.3 t/s | ~103-124.2 (slow) |
| Q4 | yes | 471k | 5519.5-6655.8 t/s | ~184-221.9 (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 Theseus 6/768?▶
Yes. At Q4 it generates ~5519.5-6655.8 tok/s and fits up to 471k context; beyond that it spills to SSD swap and slows to ~184-221.9 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.