🔌
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 48GB run GPT-2 (124M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (124M) on the Apple M3 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 633k | 1096.8-1322.6 t/s | ~27.4-33.1 (slow) |
| Q8 | yes | 634k | 2193.5-2645.2 t/s | ~54.8-66.1 (slow) |
| Q4 | yes | 635k | 3917.1-4723.5 t/s | ~97.9-118.1 (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 48GB run GPT-2 (124M)?▶
Yes. At Q4 it generates ~3917.1-4723.5 tok/s and fits up to 635k context; beyond that it spills to SSD swap and slows to ~97.9-118.1 tok/s.
How much context fits?▶
At Q4, up to about 635k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.