🔌
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 M1 Max 64GB run Nanbeige2-16B-Chat?
Yes — here's how fast and up to what context, with real measured numbers.
Nanbeige2-16B-Chat on the Apple M1 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 93k | 8.6-10.4 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 154k | 17.2-20.8 t/s | ~0.4-0.5 (slow) |
| Q4 | yes | 180k | 30.7-37.1 t/s | ~0.8-0.9 (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 M1 Max 64GB run Nanbeige2-16B-Chat?▶
Yes. At Q4 it generates ~30.7-37.1 tok/s and fits up to 180k context; beyond that it spills to SSD swap and slows to ~0.8-0.9 tok/s.
How much context fits?▶
At Q4, up to about 180k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.