🔌
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 48GB run BIDAF?
Yes — here's how fast and up to what context, with real measured numbers.
BIDAF on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 636k | 71400-86100 t/s | ~1307.7-1576.9 (slow) |
| Q8 | yes | 636k | 142800-172200 t/s | ~2615.4-3153.8 (slow) |
| Q4 | yes | 636k | 255000-307500 t/s | ~4670.3-5631.9 (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 48GB run BIDAF?▶
Yes. At Q4 it generates ~255000-307500 tok/s and fits up to 636k context; beyond that it spills to SSD swap and slows to ~4670.3-5631.9 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.