🔌
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 Novae?
Yes — here's how fast and up to what context, with real measured numbers.
Novae on the Apple M3 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 635k | 4250-5125 t/s | ~106.3-128.1 (slow) |
| Q8 | yes | 636k | 8500-10250 t/s | ~212.5-256.3 (slow) |
| Q4 | yes | 636k | 15178.6-18303.6 t/s | ~379.5-457.6 (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 Novae?▶
Yes. At Q4 it generates ~15178.6-18303.6 tok/s and fits up to 636k context; beyond that it spills to SSD swap and slows to ~379.5-457.6 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.