🔌
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 M2 Max 96GB run TinyBert?
Yes — here's how fast and up to what context, with real measured numbers.
TinyBert on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1293k | 2029.9-2447.8 t/s | ~50.7-61.2 (slow) |
| Q8 | yes | 1294k | 4059.7-4895.5 t/s | ~101.5-122.4 (slow) |
| Q4 | yes | 1295k | 7249.5-8742 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 M2 Max 96GB run TinyBert?▶
Yes. At Q4 it generates ~7249.5-8742 tok/s and fits up to 1295k 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 1295k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.