🔌
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 TinyBert?
Yes — here's how fast and up to what context, with real measured numbers.
TinyBert on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 854k | 2770.7-3341.2 t/s | ~50.7-61.2 (slow) |
| Q8 | yes | 855k | 5541.5-6682.4 t/s | ~101.5-122.4 (slow) |
| Q4 | yes | 855k | 9895.5-11932.8 t/s | ~181.2-218.6 (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 TinyBert?▶
Yes. At Q4 it generates ~9895.5-11932.8 tok/s and fits up to 855k context; beyond that it spills to SSD swap and slows to ~181.2-218.6 tok/s.
How much context fits?▶
At Q4, up to about 855k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.