🔌
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 DeBERTaV3large?
Yes — here's how fast and up to what context, with real measured numbers.
DeBERTaV3large on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1283k | 325.4-392.3 t/s | ~8.1-9.8 (slow) |
| Q8 | yes | 1289k | 650.7-784.7 t/s | ~16.3-19.6 (slow) |
| Q4 | yes | 1292k | 1162-1401.2 t/s | ~29-35 (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 DeBERTaV3large?▶
Yes. At Q4 it generates ~1162-1401.2 tok/s and fits up to 1292k context; beyond that it spills to SSD swap and slows to ~29-35 tok/s.
How much context fits?▶
At Q4, up to about 1292k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.