🔌
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 OpenThaiGPT v1.0.0 (13B)?
Yes — here's how fast and up to what context, with real measured numbers.
OpenThaiGPT v1.0.0 (13B) on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 358k | 10.4-12.5 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 438k | 20.8-25 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 473k | 37.1-44.7 t/s | ~0.9-1.1 (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 M2 Max 96GB run OpenThaiGPT v1.0.0 (13B)?▶
Yes. At Q4 it generates ~37.1-44.7 tok/s and fits up to 473k context; beyond that it spills to SSD swap and slows to ~0.9-1.1 tok/s.
How much context fits?▶
At Q4, up to about 473k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.