🔌
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 M4 Max 36GB run Prithvi WxC?
Yes — here's how fast and up to what context, with real measured numbers.
Prithvi WxC on the Apple M4 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 401k | 80.7-97.3 t/s | ~1.5-1.8 (slow) |
| Q8 | yes | 436k | 161.4-194.7 t/s | ~3-3.6 (slow) |
| Q4 | yes | 452k | 288.3-347.6 t/s | ~5.3-6.4 (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 M4 Max 36GB run Prithvi WxC?▶
Yes. At Q4 it generates ~288.3-347.6 tok/s and fits up to 452k context; beyond that it spills to SSD swap and slows to ~5.3-6.4 tok/s.
How much context fits?▶
At Q4, up to about 452k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.