🔌
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 Ultra 192GB run CodeT5-large?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-large on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2590k | 353.2-426 t/s | ~4.4-5.3 (slow) |
| Q8 | yes | 2602k | 706.5-851.9 t/s | ~8.8-10.6 (slow) |
| Q4 | yes | 2607k | 1261.6-1521.3 t/s | ~15.8-19 (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 Ultra 192GB run CodeT5-large?▶
Yes. At Q4 it generates ~1261.6-1521.3 tok/s and fits up to 2607k context; beyond that it spills to SSD swap and slows to ~15.8-19 tok/s.
How much context fits?▶
At Q4, up to about 2607k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.