🔌
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 48GB run Mamba 2, 2.7B?
Yes — here's how fast and up to what context, with real measured numbers.
Mamba 2, 2.7B on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 554k | 68.8-82.9 t/s | ~1.3-1.5 (slow) |
| Q8 | yes | 595k | 137.5-165.8 t/s | ~2.5-3 (slow) |
| Q4 | yes | 613k | 245.6-296.1 t/s | ~4.5-5.4 (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 48GB run Mamba 2, 2.7B?▶
Yes. At Q4 it generates ~245.6-296.1 tok/s and fits up to 613k context; beyond that it spills to SSD swap and slows to ~4.5-5.4 tok/s.
How much context fits?▶
At Q4, up to about 613k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.