🔌
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 Tranception?
Yes — here's how fast and up to what context, with real measured numbers.
Tranception on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 835k | 265.2-319.8 t/s | ~4.9-5.9 (slow) |
| Q8 | yes | 845k | 530.4-639.6 t/s | ~9.7-11.7 (slow) |
| Q4 | yes | 850k | 947.1-1142.1 t/s | ~17.3-20.9 (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 M4 Max 64GB run Tranception?▶
Yes. At Q4 it generates ~947.1-1142.1 tok/s and fits up to 850k context; beyond that it spills to SSD swap and slows to ~17.3-20.9 tok/s.
How much context fits?▶
At Q4, up to about 850k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.