🔌
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 M3 Max 64GB run GPT-2 (774M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (774M) on the Apple M3 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 832k | 175.7-211.9 t/s | ~4.4-5.3 (slow) |
| Q8 | yes | 844k | 351.4-423.8 t/s | ~8.8-10.6 (slow) |
| Q4 | yes | 849k | 627.5-756.7 t/s | ~15.7-18.9 (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 M3 Max 64GB run GPT-2 (774M)?▶
Yes. At Q4 it generates ~627.5-756.7 tok/s and fits up to 849k context; beyond that it spills to SSD swap and slows to ~15.7-18.9 tok/s.
How much context fits?▶
At Q4, up to about 849k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.