🔌
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 128GB run FvFold?
Yes — here's how fast and up to what context, with real measured numbers.
FvFold on the Apple M4 Max 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1735k | 20156.8-24306.7 t/s | ~369.2-445.2 (slow) |
| Q8 | yes | 1735k | 40313.6-48613.5 t/s | ~738.3-890.4 (slow) |
| Q4 | yes | 1735k | 71988.6-86809.8 t/s | ~1318.5-1589.9 (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 128GB run FvFold?▶
Yes. At Q4 it generates ~71988.6-86809.8 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~1318.5-1589.9 tok/s.
How much context fits?▶
At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.